News – Education Next

Choice Reconsidered

Frederick Hess — Wed, 31 May 2023 09:00:59 +0000

Educational choice has been woven into the fabric of American education from the nation’s earliest days.

Discussions of school choice frequently fall into familiar morality plays: Either you’re for empowering parents or supporting public education. The resulting debate manages to miss much of what matters. It ignores that all kinds of choices are hard-wired into American public education. It skips past the fact that the affluent already choose schools when purchasing homes, so the debate is really about the options available to everyone else.

Families want more options, but that fact doesn’t mean they dislike their local schools (much less, that they’re eager to flee them). In 2022, for instance, more than three-quarters of parents said that they were satisfied with their child’s experience in a public district school even as more than seven in ten endorsed education savings accounts, school vouchers, and charter schools. In short, parents overwhelmingly like both their child’s public school and school choice policies. They don’t see a tension here.

How can that be? How do we reconcile parent support for more choices with affection for their local public schools? It’s not hard, really. Parents want alternatives when it comes to scheduling, school safety, or instructional approach. They want to be able to protect their kids from bullies or from school practices they find troubling. At the same time, though, they also value schools as community anchors, they like their kid’s teachers, and they may live where they do precisely because they like the local schools.

Families can embrace options without wanting to abandon their local public schools. The notion that one is either for empowering parents or supporting public education is a misleading one. Real parents don’t think this way.

So, how does a Rethinker approach the school choice debate? It helps to start not with sweeping ideological claims but by asking how expanding options might work for students, meet the needs of families, and empower educators.

Choice Is Woven Into the Fabric of American Schooling

Amidst today’s partisan sniping, it can be easy to forget that educational choice has been woven into the fabric of American education from the nation’s earliest days. During the colonial era, it was presumed that most children would get only a rudimentary education and that only a tiny handful of affluent white families would choose to have their sons pursue more formal education (often to prepare for the ministry). Schools were routinely located in churches, and local church leaders were charged with choosing the schoolteacher. In that era, the notion that there was any tension between parental choice, the role of religion, and public provision would’ve been deemed an odd one!

In recent decades, as charter schools have grown to enroll more than 3 million students, the tapestry of options has grown to increasingly include scholarship (or voucher) programs, education savings accounts, microschools and learning pods, course choice options, hybrid homeschooling, and more.

Thinking More Expansively About Choice

Choice isn’t only an integral part of the American education landscape—it’s embedded in public schools themselves. From start to finish, schooling is a stew of choices made by parents, students, educators, system officials, and policymakers. Parents choose whether to send their children to pre-K, when to start kindergarten, or whether to opt their child out of sex education. Students choose groups and activities, which electives to take, and what book to read for a book report. Teachers choose where to apply for a job, which materials they use, and how to deliver instruction. District staff choose policies governing discipline, curricula, field trips, and attendance zones.

Outside of school, we take for granted that families will choose childcare providers, pediatricians, dentists, babysitters, and summer programs. Indeed, many such choices involve parents or guardians making decisions that are subsidized by government funds. And the choices they make will have big implications for a child’s health, well-being, upbringing, and education.

The same options that appeal to families can empower teachers and school leaders who feel stuck in unresponsive schools or systems. Educators, like parents, can value public education while wanting more opportunities to find or create learning environments where they’ll be free from entrenched rules, regulations, contract provisions, and customs.

The Lessons of Learning Pods

Learning pods offer one intriguing way to rethink the boundary between schooling, tutoring, and study groups. A learning pod is a handful of students who study together, under the auspices of a tutor, outside of a traditional school setting (mostly to augment school-based instruction rather than replace it). Learning pods leapt into the public eye during the pandemic, as families caught up in remote learning sought to provide their kids an organized, intimate, and supportive environment.

Now, learning pods might be an artifact of Covid-19 and easy to see as a bit of a “that-was-then” time capsule. Fair enough. Even if that ultimately proves to be the case, though, there are some terrific takeaways here.

The tens of thousands of learning pods that emerged across the country were most commonly described as something akin to sustained, high-intensity tutoring. Kids got customized attention in a comfortable, face-to-face environment. While learning pods may have been largely a makeshift response, more than half of families and three-quarters of instructors said they preferred their pod experiences to prior experiences in school.

Researchers studying learning pods found that, by 3-to-1, parents said that their kids felt more “known, heard, and valued” than they had in school and that, by 2-to-1, children were more engaged in their learning. Contrasting the intimate pod experience with the “anonymity” of school, one parent explained, “There’s no getting lost in this. In the pod, there’s no sneaking by without getting your work done like there would be in school.”

So, are pods a good idea? It depends. It depends on what they’re used for and how they’re constructed. But it’s not hard to imagine them providing more intensive support or an alternative learning environment for students who are struggling in a conventional classroom. School systems could help interested parents find one another, connect with local resources, and locate a qualified instructor; such aid could be especially valuable for low-income or non-English speaking families, who might find the option appealing but struggle to organize or finance learning pods on their own.

Microschools and Charter Teachers

Microschools are really small schools which provide the occasion to radically rethink the teacher’s role and the contours of the schoolhouse. Microschools typically have a few dozen students (or even fewer), who usually attend in person. The schools employ one (or a handful) of teachers to lead instruction. Unlike most learning pods, microschools aren’t supplemental programs; they are a child’s school.

For students lost amidst the oft-impersonal rhythms of institutional life, the intimate scale can be reassuring. This kind of environment may be a better fit for students who struggle with discipline or behavior in a conventional classroom. It also can allow for more personalization, parent-teacher collaboration, or advanced learning than the standard schoolhouse allows.

At the same time, microschools pose a host of challenges. How do they handle infrastructure? Teacher absences? Coverage of a full curriculum? What would it look like for school or system leaders to have the ability to arrange for internal microschools? The answers are very much a work in progress.

One particular version of microschooling is the “charter teacher” model, which would enable teachers to get state-granted authorization to operate autonomous classrooms within traditional district schools. Charter teachers would have wide latitude to hire assistants, choose how many students to instruct, decide how many classes they’d teach, and determine their own instructional model. Teachers would agree to be held accountable for student outcomes and only teach students whose parents choose to enroll their child with that teacher.

For a sense of how this might work, consider the pediatric model. Pediatricians typically work in partnerships, have a significant say when it comes to scheduling and hiring support staff, and choose how many patients to serve. At the same time, of course, patients are free to choose their pediatric practice and their pediatrician. (In one sense, the “charter teacher” approach simply democratizes access to the “choose-your-teacher” machinations regularly employed by connected parents who know how to pressure principals and work the system). Teachers disenchanted by large bureaucracies would have new freedom, while more flexible or part-time options could draw former educators back into the profession.

The charter teacher model isn’t currently in use. Putting it into practice would require state officials to establish a process by which teachers could demonstrate professional mastery or a record of high student achievement. Qualified teachers could obtain small grants to launch their own practices, after which they’d be funded on a per pupil basis developed by the school district.

Hybrid Homeschooling

It may be hard to fathom today but, a half-century ago, homeschooling was illegal across most of the U.S. A series of legal and political battles in the 1970s and 1980s changed that. By 2020, more than three million children a year were being homeschooled, a number that increased dramatically during the Covid-19 pandemic. But just what does it mean to “homeschool” a child?

While the term “homeschooling” may bring to mind a picture of a parent and a child sitting at a kitchen table, the reality is that most homeschool families make extensive use of networks, online resources, tutors, and much else. Indeed, the difference between homeschooling and a learning pod (or a microschool) is often just a matter of degree.

In the wake of the pandemic, there was broad interest in education options that incorporate more of what homeschooling provides. In 2022, two-thirds of parents with children in special education said they’d like a school schedule which had their child learning at home at least one day a week (though just 15 percent of parents wanted to do full-time homeschooling). Among other parents, more than half said they’d like to have their child home at least one day a week. Oh, and just over half of teens said they’d like to learn at home at least one day a week.

In other words, lots of parents and students are interested in maintaining some of the parent-child interaction they experienced during the pandemic but don’t want to be “homeschoolers.” Hybrid homeschooling seeks to provide what those families are seeking, with students enrolling in school for part of the week and learning from home for the other part. More than 1,000 hybrid homeschools have emerged across the country in recent years. Many are private schools, others are charter schools, and a handful are part of traditional school districts.

Arrangements can play out in many ways. A hybrid homeschool might have students in the building four days a week, with different classes (or grades) of students learning from home on different days. It might have all students learning at home on Mondays or Wednesdays or on certain mornings or afternoons. Some schools are more prescriptive when it comes to curricula, while others leave more to parent discretion. For younger children, parents generally play a much larger instructional role, while there’s more independent study for older children.

The feasibility of such arrangements depends on the laws of a given state, but school and system leaders may find state policies and federal regulations more accommodating than they’d have thought. In Idaho, for instance, if homeschool students use district programming on even a part-time basis, they’re included in district attendance counts for state funding. This has, not surprisingly, made it easier for districts to support homeschool families. And Idaho is far from alone—at least a dozen states have similar arrangements, although the rules vary with regards to services, student eligibility, and how funding works.

The Possibilities of Course Choice

Another approach to educational choice is course choice. Course choice is a way to move new options into a student’s current school rather than to move a student to a new school.

While some families want to switch schools, I noted a bit earlier that more than 70 percent of parents consistently say they’re satisfied with their child’s school. Of course, this doesn’t mean those parents like everything about their school. Families may want students to stay with friends, familiar teachers, and established routines but also have access to alternative courses. Overall satisfaction with a school doesn’t necessarily reflect satisfaction with the arts program, math curriculum, reading instruction, Advanced Placement offerings, or what-have-you. Even pre-pandemic, parents who liked their school might have still grumbled about these things. Now, with so many students forcibly acclimated to a variety of remote learning options and providers, it seems only sensible that students should be able to take advantage of such options without changing schools.

The notion of “course choice” allows students to tap into instructional options that aren’t available at a student’s school. Course choice gives students the ability to take courses beyond those offered by their local school district. These courses may be offered by neighboring districts, state higher education institutions, virtual learning providers, or specialized tutoring services. Course choice laws typically specify that a portion of the student’s per pupil outlay can be used to pay the costs of enrollment.

Students may be able to access courses in chemistry, constitutional law, or AP calculus even if their school lacks a chemistry teacher, a constitutional law class, or an AP math program. This can be a solution for small schools dealing with staffing constraints, struggling to attract teachers in certain subjects or fields, or where only a tiny number of students want to enroll in a given class.

Course choice programs can come in many flavors. New Hampshire’s “Learn Everywhere” program allows high school students to earn a “certificate of credit” from any program recognized by the state board of education which can demonstrate that students have met the learning objectives.

Course choice allows students in a high school with a short-staffed science department to still study advanced physics. And it can make it possible for students to study robotics or Russian, even if their school lacks the requisite staff. If this all sounds pretty far removed from our heated debates about school choice, you’ve got the idea.

Parents value schools as community anchors.

What about Bad Choices?

Parents may make bad choices, just as with day care or dentists. But we also reasonably presume that parents will make better choices when they have better information. So, how can we supply the kind of information that can help parents make good choices?

State tests and other academic assessments are one useful, consistent gauge. While such data is necessary, few parents or teachers think it’s sufficient. Thus, it’s crucial to consider other ways to ensure quality. There is an array of potential tools, including:

Professional, systematic ratings of customer satisfaction, something akin to the information reported by sources like J.D. Powers and Associates. These make it easy for consumers to draw on the judgments of other users.
Scientific evaluations by credible third parties, such as those offered by Consumer Reports. Such objective evaluations allow experts to put new educational offerings through their paces and then score them on relevant dimensions of performance, as well as price.
Expert evaluation of services like those provided by health inspectors (or, in schooling, the famous example of the British School Inspectorate). Such evaluation focuses on examining processes and hard-to-measure outcomes, drawing on informed, subjective judgment.
Reports reflecting user experiences—essentially, drawing on the wisdom of crowds. Online providers routinely allow users to offer detailed accounts of the good and bad they’ve experienced, and the public to readily view what they have to say. While these results aren’t systematic or scientific, they are very good at providing context and color.

Of course, even with terrific information, parents can still make bad choices about schooling. But that’s true of pretty much anyone involved in schools: Teachers can make bad choices when deciding how to support a struggling student or design an individualized education program. Administrators can make bad choices when assigning a student to a school or teacher.

Schooling is suffused with choices. We should certainly ask what happens when a parent makes a poor choice. But we must also question the consequences of restrictive policies which limit parents’ ability to find better educational options for their kids.

Rethinking School Choice

It’s odd that the discussion of school choice has so often taken the shape of heated argument, given the intuitive appeal of the idea that all parents (rich and poor alike) should have a say in their kids’ schooling.

Our familiar fights are both distracting and odd. Consider that in a field like healthcare, even those most passionate about universal, publicly funded coverage still believe that individuals should be free to choose their own doctor. In housing, even the most ardent champion of public housing thinks families should get to choose where they live. There’s no debate about whether families should have agency when it comes to such high-stakes decisions in health care or housing. The same logic should apply in schooling. It’s not selfish or risky for parents to want a say in who teaches their kids or where their kids go to school. It’s normal.

It’s downright weird that educational choice has focused so narrowly on students changing schools. After all, we live in an era when extraordinary options have become routinely available.

In the end, the real promise of choice isn’t just that it can help students escape struggling schools. It’s that it can help make room for parents and educators alike to rethink how they want schools to work.

Adapted with permission from Hess, F. M. (2023). The Great School Rethink. Harvard Education Press.

The post Choice Reconsidered appeared first on Education Next.

Is Ron DeSantis’s Education Record Anything to Emulate?

William Mattox — Tue, 23 May 2023 09:00:04 +0000

Florida Gov. Ron DeSantis reacts after signing a bill to expand school choice across Florida during a press conference at Christopher Columbus High School on Monday, March 27, 2023, in Miami.

The governor of Florida, Ron DeSantis, has emerged in recent years as a nationally significant political figure and a possible Republican presidential contender in part on the basis of his record in K–12 education. What has he actually accomplished in Florida? Are his tactics there worth emulating elsewhere, or would they best be avoided? William Mattox, the director of the Marshall Center for Educational Options at the James Madison Institute in Tallahassee, Florida, who is a registered independent, offers a more positive assessment, while Cathy Young, a fellow at the Cato Institute who also writes for The Bulwark, Newsday, and Reason, is more cautious about what DeSantis has done.

DeSantis defends values while expanding choice to de-escalate the stakes
By William Mattox

DeSantis fights a counterproductive culture war in Florida’s schools
By Cathy Young

The post Is Ron DeSantis’s Education Record Anything to Emulate? appeared first on Education Next.

School Number 500 to School Number 50: What’s the Difference?

Stephanie McCoy — Wed, 17 May 2023 09:00:37 +0000

In our old neighborhood, sirens blaring were daily background noise.

Our family recently encountered a life-changing event: a move. We spent 16 years in our previous home, and in the summer of 2022, we moved across town. In Portland, Oregon, where we live, elementary school assignment is mainly on the basis of a student’s residence, so the new house also meant a new school for our two kids, who are in 2nd and 4th grade.

Although we’ve only been part of the new school community for seven months, I have already noticed huge differences between the two schools. Online rankings from various comparison websites labeled the new school as significantly better. Precisely what that looks like for students and parents became clear and concrete over time.

The first big difference I noticed was within the new neighborhood. Our previous school was located in a highly impoverished area. Sadly, that factor brought a lot of crime. Shoplifting, drug-use, and violence were regular occurrences near our old home. Sirens blaring were daily background noise. A walk to the store meant likely exposure to people using drugs or fighting. Unfortunately, many of the homeless people that we encountered were aggressive. This lack of safety was the number one reason for our move.

Our new neighborhood is incredibly safe and quiet. The only noises we hear are neighbors chatting and dogs barking. Our neighbors and nearby residents seem happy, healthy, and involved in their community. Our new neighborhood has many more resources and a higher average income than our previous neighborhood.

One difference I’ve noticed within the school is the level of involvement from the school community and Parent Teacher Association. I work as a “classroom lead” for my son’s classroom, helping the teacher with family communication, school fundraising, and general coordination on classroom matters. So I’m constantly asking for donations, chaperones, and volunteers. I was shocked the first time I asked for chaperones for a field trip. I asked for five, and within minutes I had seven. It was the same when I asked for donations toward the teacher’s Christmas gift. Within a few days, I had $325! Every time I ask for anything for the school or classroom, the goal is met and exceeded immediately.

Our old school struggled with donations and fundraising. The volunteers and chaperones came in smaller numbers. This makes sense, because the neighborhood had a lower average income. Caregivers weren’t as available for volunteer and chaperone opportunities, because many of them had to work.

Another difference I found was that our old school tended to offer free financial and language resources, while our new school offers classes, events, and materials at a cost. I remember many events at our old school that would involve handing out art sets, food, and other items to families, and the school would put together a family night and provide a dinner and entertainment for free. This school year, we were floored that at the Halloween carnival, our new school charged admission and sold concessions. I think this is a good difference. The impoverished school shouldn’t charge admission to low-income families, and it seems fair to me that a school in a middle-class neighborhood would charge admission.

The biggest difference I have found between the two schools sits between the classroom walls: behavior. Our old school, where I worked as an instructional assistant, had some shocking statistics on behavior referrals last year. I remember sitting through a staff meeting looking over slides, and the number of incidents was just heartbreaking. A lot of kids would leave the classroom, destroy educational materials, and get into physical altercations. My son would get frustrated on a regular basis because these disruptions affected his learning. He would simply have to sit and wait while a student disrupted a lesson because there weren’t behavior specialists to assist. I brought this concern to his new teacher at his new school and he simply said, “I think Atticus is in for a pleasant surprise, because those things very rarely happen here.” Seven months later, my son hasn’t reported an incident yet. If there are behavior problems, they are dealt with swiftly and out of the classroom.

Resources are one big difference between a low-ranking and high-ranking school. Is the school properly staffed? Is the staff being continually educated? Does the neighborhood have financial resources? Is the school community active? The per-pupil spending at the old school, at nearly $22,000 a year, was actually considerably more than at the new school, which spends about $16,000 a year, so “resources” can mean a lot more than just how much money the government spends on operating a school.

My family managed to afford the move to the more expensive neighborhood and the higher-ranked school only after a couple of small inheritances and years of savings. If more people could see firsthand the differences between the two schools, though, maybe there’d be increased political support for allowing students access to safer, better-resourced schools in ways that don’t require a family to move across town.

Stephanie McCoy is a writer and mom in Oregon.

The post School Number 500 to School Number 50: What’s the Difference? appeared first on Education Next.

California’s New Math Framework Doesn’t Add Up

Tom Loveless — Tue, 16 May 2023 09:00:12 +0000

A bumpy road is ahead for California’s proposed new math framework.

California’s proposed math curriculum framework has ignited a ferocious debate, touching off a revival of the 1990s math wars and attracting national media attention. Early drafts of the new framework faced a firestorm of criticism, with opponents charging that the guidelines sacrificed accelerated learning for high achievers in a misconceived attempt to promote equity.

The new framework, first released for public comment in 2021, called for all students to take the same math courses through 10th grade, a “detracking” policy that would effectively end the option of 8th graders taking algebra. A petition signed by nearly 6,000 STEM leaders argued that the framework “will have a significant adverse effect on gifted and advanced learners.” Rejecting the framework’s notions of social justice, an open letter with over 1,200 signatories, organized by the Independent Institute, accused the framework of “politicizing K–12 math in a potentially disastrous way” by trying “to build a mathless Brave New World on a foundation of unsound ideology.”

About once every eight years, the state of California convenes a group of math educators to revisit the framework that recommends how math will be taught in the public schools. The current proposal calls for a more conceptual approach toward math instruction, deemphasizing memorization and stressing problem solving and collaboration. After several delays, the framework is undergoing additional edits by the state department of education and is scheduled for consideration by the state board of education for approval sometime in 2023.

Why should anyone outside of California care? With almost six million public school students, the state constitutes the largest textbook market in the United States. Publishers are likely to cater to that market by producing instructional materials in accord with the state’s preferences. California was ground zero in the debate over K–12 math curriculum in the 1990s, a conflict that eventually spread coast to coast and around the world. A brief history will help set the stage.

Historical Context

Standards define what students are expected to learn—the knowledge, skills, and concepts that every student should master at a given grade level. Frameworks provide guidance for meeting the standards—including advice on curriculum, instruction, and assessments. The battle over the 1992 California state framework, a document admired by math reformers nationwide, started slowly, smoldered for a few years, and then burst into a full-scale, media-enthralling conflict by the end of the decade. That battle ended in 1997 when the math reformers’ opponents, often called math traditionalists, convinced state officials to adopt math standards that rejected the inquiry-based, constructivist philosophy of existing state math policy.

The traditionalists featured a unique coalition of parents and professional mathematicians—scholars in university mathematics departments, not education schools—who were organized via a new tool of political advocacy: the Internet.

The traditionalist standards lasted about a decade. By the end of the aughts, the standards were tarnished by their association with the unpopular No Child Left Behind Act, which mandated that schools show all students scoring at the “proficient” level on state tests by 2014 or face consequences. It was clear that virtually every school in the country would be deemed a failure, No Child Left Behind had plummeted in the public’s favor, and policymakers needed something new. Enter the Common Core State Standards.

The Common Core authors wanted to avoid a repeat of the 1990s math wars, and that meant compromise. Math reformers were satisfied by the standards’ recommendation that procedures (computation), conceptual understanding, and problem solving receive “equal emphasis.” Traditionalists were satisfied with the Common Core requirement that students had to master basic math facts for addition and multiplication and the standard algorithms (step-by-step computational procedures) for all four operations—addition, subtraction, multiplication, and division.

California is a Common Core state and, for the most part, has avoided the political backlash that many states experienced a few years after the standards’ widespread adoption. The first Common Core–oriented framework, published in 2013, was noncontroversial; however, compromises reflected in the careful wording of some learning objectives led to an unraveling when the framework was revised and presented for public comment in 2021.

Unlike most of the existing commentary on the revised framework, my analysis here focuses on the elementary grades and how the framework addresses two aspects of math: basic facts and standard algorithms. The two topics are longstanding sources of disagreement between math reformers and traditionalists. They were flashpoints in the 1990s math wars, and they are familiar to most parents from the kitchen-table math that comes home from school. In the case of the California framework, these two topics illustrate how reformers have diverged from the state’s content standards, ignored the best research on teaching and learning, and relied on questionable research to justify the framework’s approach.

Jo Boaler is a math education professor at Stanford and member of the California Math Framework writing committee.

Addition and Multiplication Facts

Fluency in mathematics usually refers to students’ ability to perform calculations quickly and accurately. The Common Core mathematics standards call for students to know addition and multiplication facts “from memory,” and the California math standards expect the same. The task of knowing basic facts in subtraction and division is made easier by those operations being the inverse, respectively, of addition and multiplication. If one knows that 5 + 6 = 11, then it logically follows that 11 – 6 = 5; and if 8 × 9 = 72, then surely 72 ÷ 9 = 8.

Cognitive psychologists have long pointed out the value of automaticity with number facts—the ability to retrieve facts immediately from long-term memory without even thinking about them. Working memory is limited; long-term memory is vast. In that way, math facts are to math as phonics is to reading. If these facts are learned and stored in long-term memory, they can be retrieved effortlessly when the student is tackling more-complex cognitive tasks. In a recent interview, Sal Khan, founder of Khan Academy, observed, “I visited a school in the Bronx a few months ago, and they were working on exponent properties like: two cubed, to the seventh power. So, you multiply the exponents, and it would be two to [the] 21st power. But the kids would get out the calculator to find out three times seven.” Even though they knew how to solve the exponent exercise itself, “the fluency gap was adding to the cognitive load, taking more time, and making things much more complex.”

California’s proposed framework mentions the words “memorize” and “memorization” 27 times, but all in a negative or downplaying way. For example, the framework states: “In the past, fluency has sometimes been equated with speed, which may account for the common, but counterproductive, use of timed tests for practicing facts. . . . Fluency is more than the memorization of facts or procedures, and more than understanding and having the ability to use one procedure for a given situation.” (All framework quotations here are from the most recent public version, a draft presented for the second field review, a 60-day public-comment period in 2022.)

One can find the intellectual origins of the framework on the website of Youcubed, a Stanford University math research center led by Jo Boaler, who is a math education professor at Stanford and member of the framework writing committee. Youcubed is cited 28 times in the framework, including Boaler’s essay on that site, “Fluency without Fear: Research Evidence on the Best Ways to Learn Math Facts.” The framework cites Boaler an additional 48 times.

The framework’s attempt to divorce fluency from speed (and from memory retrieval) leads it to distort the state’s math standards. “The acquisition of fluency with multiplication facts begins in third grade and development continues in grades four and five,” the framework states. Later it says, “Reaching fluency with multiplication and division within 100 represents a major portion of upper elementary grade students’ work.”

Both statements are inaccurate. The state’s 3rd-grade standard is that students will know multiplication facts “from memory,” not that they will begin fluency work and continue development in later grades. After 3rd grade, the standards do not mention multiplication facts again. In 4th grade, for example, the standards call for fluency with multidigit multiplication, a stipulation embedded within “understanding of place value to 1,000,000.” Students lacking automaticity with basic multiplication facts will be stopped cold. Parents who are concerned that their 4th graders don’t know the times tables, let alone how to multiply multidigit numbers, will be directed to the framework to justify children falling behind the standards’ expectations.

After the release of Common Core, the authors of the math standards published “Progressions” documents that fleshed out the standards in greater detail. The proposed framework notes approvingly, “The Progressions for the Common Core State Standards documents are a rich resource; they (McCallum, Daro, and Zimba, 2013) describe how students develop mathematical understanding from kindergarten through grade twelve.” But the Progressions contradict the framework on fluency. They state: “The word fluent is used in the Standards to mean ‘fast and accurate.’ Fluency in each grade involves a mixture of just knowing some answers, knowing some answers from patterns (e.g., ‘adding 0 yields the same number’), and knowing some answers from the use of strategies.”

Students progress toward fluency in a three-stage process: use strategies, apply patterns, and know from memory. Students who have attained automaticity with basic facts have reached the top step and just know them, but some students may take longer to commit facts to memory. As retrieval takes over, the possibility of error declines. Students who know 7 × 7 = 49 but must “count on” by 7 to confirm that 8 × 7 = 56 are vulnerable to errors to which students who “just know” that 7 × 8 = 56 are impervious. In terms of speed, the analogous process in reading is decoding text. Students who “just know” certain words because they have read them frequently are more fluent readers than students who must pause to sound out those words phonetically. This echoes the point Sal Khan made about students who know how to work with exponents raised to another power but still need a calculator for simple multiplication facts.

Sal Khan, the founder of Khan Academy, observed that, “the fluency gap was adding to the cognitive load, taking more time, and making things much more complex.”

Standard Algorithms

Algorithms are methods for solving multi-digit calculations. Standard algorithms are simply those used conventionally. Learning the standard algorithms of addition, subtraction, multiplication, and division allows students to extend single-digit knowledge to multi-digit computation, while being mindful of place value and the possible need for regrouping.

Barry Garelick, a math teacher and critic of Common Core, posted a series of blog posts about the standards and asked, “Can one teach only the standard algorithm and meet the Common Core State Standards?” Jason Zimba, who is one of three authors of the Common Core math standards, responded:

Provided the standards as a whole are being met, I would say that the answer to this question is yes. The basic reason for this is that the standard algorithm is “based on place value [and] properties of operations.” That means it qualifies. In short, the Common Core requires the standard algorithm; additional algorithms aren’t named, and they aren’t required.

Zimba provides a table showing how exclusively teaching the standard algorithms of addition and subtraction could be accomplished, presented not as a recommendation, but as “one way it could be done.” Zimba’s approach begins in 1st grade, with students—after receiving instruction in place value—learning the proper way to line up numbers vertically. “Whatever one thinks of the details in the table, I would think that if the culminating standard in grade 4 is realistically to be met, then one likely wants to introduce the standard algorithm pretty early in the addition and subtraction progression.”

Note the term “culminating standard.” That implies the endpoint of development. The framework, however, interprets 4th grade as the grade of first exposure, not the culmination—and extends that misinterpretation to all four operations with whole numbers. “The progression of instruction in standard algorithms begins with the standard algorithm for addition and subtraction in grade four; multiplication is addressed in grade five; the introduction of the standard algorithm for whole number division occurs in grade six,” the framework reads.

This advice would place California 6th graders years behind the rest of the world in learning algorithms. In Singapore, for example, division of whole numbers up to 10,000 is taught in 3rd grade. The justification for delay stated in the framework is: “Students who use invented strategies before learning standard algorithms understand base-ten concepts more fully and are better able to apply their understanding in new situations than students who learn standard algorithms first (Carpenter et al., 1997).”

The 1997 Carpenter study, however, is a poor reference for the framework’s assertion. That study’s authors declare, “Instruction was not a focus of this study, and the study says very little about how students actually learned to use invented strategies.” In addition, the study sample was not scientifically selected to be representative, and the authors warn, “The characterization of patterns of development observed in this study cannot be generalized to all students.”

As for the Progressions documents mentioned above, they do not prohibit learning standard algorithms before the grade level of the “culminating expectation.” Consistent with Jason Zimba’s approach, forms of the standard addition and subtraction algorithms are presented as 2nd grade topics, two years before students are required to demonstrate fluency.

The selective use of evidence extends beyond the examples above, as is clear from the research that is cited—and not cited—by the framework.

Research Cited by the Framework

On June 1, 2021, Jo Boaler issued a tweet asserting, “This 4 week camp increases student achievement by the equivalent of 2.8 years.” The tweet included information on a two-day workshop at Stanford for educators interested in holding a Youcubed-inspired summer camp. The Youcubed website promotes the summer camp with the same claim of additional years of learning.

Where did the 2.8 years come from? The first Youcubed math camp was held on the Stanford campus in 2015 with 83 6th and 7th graders. For 18 days, students spent mornings working on math problems and afternoons touring the campus in small groups, going on scavenger hunts, and taking photographs. The students also received instruction targeting their mathematical mindsets, learning that there is no such thing as “math people” and “nonmath people,” that being fast at math is not important, and that making mistakes and struggling, along with thinking visually and making connections between mathematical representations, promote brain growth. Big ideas, open-ended tasks, collaborative problem solving, lessons on mindset, and inquiry-based teaching—these are foundational to the framework. The camp offers a test run of the proposed framework, the document asserting that the camps “significantly increase achievement in a short period of time.”

The claim of growth is based on an assessment the researchers administered on the first and last days of the camp. The test consisted of four open-ended problems, called “tasks,” scored by a rubric, with both the problems and the rubric created by the Mathematical Assessment Research Service, or MARS. Students were given four tasks on the first day and the same four tasks on the final day of camp. An effect size of 0.91 was calculated by dividing the difference between the group’s pre- and post-test average scores by the pre-test standard deviation. How this effect size was converted into years of learning is not explained, but researchers usually do this based on typical rates of achievement growth among students taking standardized math tests in consecutive years.

In 2019, the Youcubed summer-camp program went national. An in-house study was conducted involving 10 school districts in five states where the camps served about 900 students in total and ranged from 10 to 28 days. The study concluded, “The average gain score for participating students across all sites was 0.52 standard deviation units (SD), equivalent to 1.6 years of growth in math.”

Let’s consider these reported gains in the context of recent NAEP math scores. The 2022 scores triggered nationwide concern as 4th graders’ scores fell to 236 scale score points from 241 in 2019, a decline of 0.16 standard deviations. Eighth graders’ scores declined to 274 from 282, equivalent to 0.21 standard deviations. Headlines proclaimed that two decades of learning had been wiped out by two years of pandemic. A McKinsey report estimated that NAEP scores might not return to 2019 levels until 2036.

If the Youcubed gains are to be believed, all pandemic learning losses can be restored, and additional gains achieved, by two to four weeks of summer school.

There are several reasons to doubt the study’s conclusions, the most notable of which is the lack of a comparison group to gauge the program’s effects as measured by the MARS outcome. School districts recruited students for the camps. No data are provided on the number of students approached, the number who refused, and the number who accepted but didn’t show up. The final group of participating students comprises the study’s treatment group. The claim that these students experienced 1.6 years of growth in math is based solely on the change in students’ scores on the MARS tasks between the first and last day of the program.

This is especially problematic because the researchers gave students the same four MARS tasks before and after the program. Using the exact same instrument to test and re-test students within four weeks could inflate post-treatment scores, especially if the students worked on similar problems during the camp. No data are provided confirming that the MARS tasks are suitable, in terms of technical quality, for use in estimating the summer camp’s effect. Nor do the authors demonstrate that the tasks are representative of the full range of math content that students are expected to master, which is essential to justify reporting students’ progress in terms of years of learning. Even the grade level of the tasks is unknown, although camp attendees spanned grades 5 to 7, and MARS offers three levels of tasks (novice, apprentice, and expert).

The study’s problems extend to its treatment of attrition from the treatment sample. For one of the participating school districts (#2), 47 students are reported enrolled, but the camp produces 234 test scores—a mystery that goes unexplained. When this district is omitted, the remaining nine districts are lacking pre- and post-test scores for about one-third of enrolled students, who presumably were absent on either the first or last day. The study reports attendance rates in each district as the percentage of students who attended 75 percent of the days or more, with the median district registering 84 percent. Four districts reported less than 70 percent of students meeting that attendance threshold. A conventional metric for attendance during a school year is that students who miss 10 percent of days are “chronically absent.” By that standard, attendance at the camps appears spotty at best, and in four of the 10 camps, quite poor.

These are serious weaknesses. Just as the camps serve as prototypes of the framework’s ideas about good curriculum and instruction, the studies of Youcubed summer camps are illustrative of what the framework considers compelling research. The studies do not meet minimal standards of causal evidence.

Brian Conrad, professor of mathematics at Stanford University, has analyzed the framework’s citations and documented many instances where the original findings of studies were distorted.

Research Omitted by the Framework

It is also informative to look at research that is not included in the California framework.

The What Works Clearinghouse, housed within the federal Institute of Education Sciences, publishes practice guides for educators. The guides aim to provide concise summaries of high-quality research on various topics. A panel of experts conducts a search of the research literature and screens studies for quality, following strict protocols. Experimental and quasi-experimental studies are favored because of their ability to estimate causal effects. The panel summarizes the results, linking each recommendation to supporting studies. The practice guides present the best scientifically sound evidence on causal relationships in teaching and learning.

How many of the studies cited in the practice guides are also cited in the framework? To find out, I searched the framework for citations to the studies cited by the four practice guides most relevant to K–12 math instruction. Here are the results:

Assisting Students Struggling with Mathematics: Intervention in the Elementary Grades
(2021) 0 out of 43 studies

Teaching Strategies for Improving Algebra Knowledge in Middle and High School Students
(2015, revised 2019) 0 out of 12 studies

Improving Mathematical Problem Solving in Grades 4 Through 8
(2012) 0 out of 37 studies

Developing Effective Fractions Instruction for Kindergarten Through 8th Grade
(2010) 1 out of 22 studies

Except for one study, involving teaching the number line to young children using games, the framework ignores the best research on K–12 mathematics. How could this happen?

One powerful clue: key recommendations in the practice guides directly refute the framework. Timed activities with basic facts, for example, are recommended to increase fluency, with the “Struggling Students” guide declaring “the expert panel assigned a strong level [emphasis original] of evidence to this recommendation based on 27 studies of the effectiveness of activities to support automatic retrieval of basic facts and fluid performance of other tasks involved in solving complex problems.” Calls for explicit or systematic instruction in the guides fly in the face of the inquiry methods endorsed in the framework. Worked examples, in which teachers guide students step by step from problem to solution, are encouraged in the guides but viewed skeptically by the framework for not allowing productive struggle.

Bumpy Road Ahead

The proposed California Math Framework not only ignores key expectations of the state’s math standards, but it also distorts or redefines them to serve a reform agenda. The standards call for students to know “from memory” basic addition facts by the end of 2nd grade and multiplication facts by the end of 3rd grade. But the framework refers to developing fluency with basic facts as a major topic of 4th through 6th grades. Fluency is redefined to disregard speed. Instruction on standard algorithms is delayed by interpreting the grades for culminating standards as the grades in which standard algorithms are first encountered. California’s students will be taught the standard algorithm for division years after the rest of the world.

The framework’s authors claim to base their recommendations on research, but it is unclear how—or even if—they conducted a literature search or what criteria they used to identify high-quality studies. The document serves as a manifesto for K–12 math reform, citing sources that support its arguments and ignoring those that do not, even if the omitted research includes the best scholarship on teaching and learning mathematics. Brian Conrad, professor of mathematics at Stanford University, has analyzed the framework’s citations and documented many instances where the original findings of studies were distorted. In some cases, the papers’ conclusions were the opposite of those presented in the framework.

The pandemic took a toll on math learning. To return to a path of achievement will require the effort of teachers, parents, and students. Unfortunately, if the state adopts the proposed framework in its current form, the document will offer little assistance in tackling the hard work ahead.

Tom Loveless, a former 6th-grade teacher and Harvard public policy professor, is an expert on student achievement, education policy, and reform in K–12 schools. He also was a member of the National Math Advisory Panel and U.S. representative to the General Assembly, International Association for the Evaluation of Educational Achievement, 2004–2012.

The post California’s New Math Framework Doesn’t Add Up appeared first on Education Next.

Think Reforming Teacher Pay Doesn’t Work? Think Again.

Martin R. West — Wed, 26 Apr 2023 09:00:03 +0000

American education reform in the 2010s centered largely on changing how teachers are evaluated and paid. Through Race to the Top and its state waiver program, the Obama administration successfully prodded 44 states to adopt new evaluation systems based, in part, on objective measures of student achievement. These states committed, at least on paper, to using teachers’ evaluation ratings for personnel decisions ranging from who receives tenure to who gets a bonus. In the meantime, a turbo-charged federal Teacher Incentive Fund program encouraged school districts to link educators’ compensation to their performance.

It is tempting to look back at that era and conclude that teacher-pay reform has failed—that we should move on to other strategies. Scores on the National Assessment of Educational Progress stagnated over the course of the decade, with gaps increasing between higher- and lower-performing students. A 2023 National Bureau of Economic Research working paper on the impact of state teacher-evaluation policies reports “precisely estimated null effects.” Policymakers, it seems, had already made the same estimation, for few are paying attention now to evaluation-and-pay reform.

Yet closer inspection uncovers a different story. Despite incorporating test-score evidence, the new state evaluation systems still failed at their most basic task of distinguishing the most- and least-effective educators. As Matt Kraft and Allison Gilmour report, the share of teachers rated ineffective in most settings barely budged—perhaps because the principals doing the rating knew they couldn’t fire low performers or even differentiate pay. Genuinely new approaches to evaluating teachers haven’t failed; they haven’t been widely tried.

Moreover, a growing body of evidence suggests that teacher evaluation-and-pay reform, when it is taken seriously and implemented well, produces gains. Education Next has previously reported on the consequences of the IMPACT evaluation-and-pay system implemented in Washington, D.C. under Michelle Rhee and her successor, Kaya Henderson (see “A Lasting Impact,” research, Fall 2017). In short, strong teachers improved their performance, ineffective teachers left the district, and student performance rose.

In this issue, Yale economist Barbara Biasi provides complementary evidence on the potential of performance-based pay based on Act 10, a 2011 Wisconsin law that limited the scope of collective bargaining to base pay (see “Wisconsin’s Act 10, Flexible Pay, and the Impact on Teacher Labor Markets,” features). As Biasi notes, this “allowed school districts to set pay more flexibly and without unions’ consent, in principle detaching compensation from seniority and credentials.” Act 10 also capped annual growth in base pay at the rate of inflation and required educators to pay more toward health care and pension costs. If you think that teachers should be paid both more and differently than they are now, Act 10 is not for you. But the law did give Wisconsin school districts unprecedented flexibility in setting teachers’ pay.

Not all districts took advantage. About half continued to use traditional step-and-lane salary schedules based on experience and graduate degrees. The other half, however, abandoned step-and-lane schedules and, in effect, allowed individual teachers to negotiate their pay. This natural experiment unfolded gradually across the state, due to differences in when pre-Act 10 collective-bargaining agreements expired, enabling Biasi to study the law’s effects.

She reports that, in districts adopting flexible-pay systems, teachers who were more effective in raising students’ test scores started to earn more than their peers—despite the fact that Wisconsin school districts at the time did not calculate value-added scores. (Apparently, administrators don’t need an algorithmic statewide teacher-evaluation system to identify their best performers.) These districts saw more weak teachers depart and experienced an influx of effective teachers, many of them poached from districts that stuck with seniority-based pay. Incumbent teachers in flexible-pay districts likewise improved their performance, and student achievement rose.

Act 10 did have unintended consequences. Districts serving poor students were less likely to adopt flexible pay systems. As a result, the personnel churn the law generated likely reduced these students’ access to effective teachers. A gender pay-gap emerged, as women proved less likely than male teachers to negotiate with male principals for higher salaries. The cap on growth in base pay may have kept districts from paying Wisconsin teachers more at a time when that would have been helpful.

Still, Biasi’s careful and creative research adds to the evidence that altering how teachers are evaluated and paid remains a powerful lever for improving student outcomes. It suggests that the Obama administration’s teacher-evaluation reform fell short at least in part because it wasn’t accompanied by a loosening of collective-bargaining restrictions. Act 10 reveals the value of first giving districts the flexibility needed to use what they already know about who their strongest performers are. States seeking to draw the right lessons from the past decade’s disappointments would do well to keep that in mind.

— Martin R. West

The post Think Reforming Teacher Pay Doesn’t Work? Think Again. appeared first on Education Next.

Wisconsin’s Act 10, Flexible Pay, and the Impact on Teacher Labor Markets

Barbara Biasi — Tue, 25 Apr 2023 09:00:45 +0000

Effective teachers are a vital input for schools and students. Teachers can have important and long-lasting impacts on students’ learning, college attendance, and eventual earnings. They can also reduce teen pregnancy or incarceration. Attracting effective teachers into public schools and retaining them is thus a first-order policy goal. Changes in teacher compensation, for example across-the-board raises in salaries or pay plans that directly tie salaries to performance, are often proposed as ways to achieve this goal. The debate on these reforms, though, is very much open; some opponents argue that these changes would be ineffective because teachers are not motivated by money.

Empirical evidence on the effects of compensation reform is somewhat scarce. Most U.S. public school teachers are paid according to rigid schedules that determine pay based solely on seniority and academic credentials. In unionized school districts, these schedules are set by collective bargaining agreements. The near absence of variation in pay practices has prevented rigorous evaluation of the impacts of changes in the structure of teacher pay on the supply of effective teachers and on students’ success.

The dearth of variation in pay schemes was broken in 2011 when the Wisconsin state legislature passed Act 10. Intended to help address a projected $3.6 billion budget deficit through cuts in public-sector spending, Act 10 introduced several changes concerning teachers’ unions, school districts, and their employees. First and foremost, Act 10 limited the scope of salary negotiations to base pay, preventing unions from negotiating salary schedules and including them in collective bargaining agreements. This allowed school districts to set pay more flexibly and without unions’ consent, in principle detaching compensation from seniority and credentials. Act 10 also capped annual growth in base pay to the rate of inflation and required employees to contribute more towards their pensions and health care plans. Lastly, the new legislation made it harder for unions to operate. It requires local union chapters to recertify every year with support from the absolute majority of all employees they represent, and it prohibits automatic collection of union dues from employees’ paychecks.

The public debate over Act 10 has focused on whether the reform package was good or bad for students, schools, and teachers. The unions vigorously opposed the legislation, organizing protests and occupying the state capitol building. Republican Governor Scott Walker just as vigorously defended the legislation, which helped propel him to national prominence. For education policy scholars, however, what is undeniable is that the legislation was useful, because its implementation offered an opportunity to study its effects. In a series of studies, I have taken advantage of the changes to teachers’ labor markets introduced by the reform to shed light on the impact of flexible pay on teachers’ mobility and effectiveness, the gender wage gap among teachers, and whether most teachers would prefer higher salaries today versus more generous pensions when they retire.

Learning from Act 10

The provisions of Act 10 went into effect immediately. In practice, though, school districts acquired the power to use their newly acquired flexibility not simultaneously, but at different points in time. The two-year collective bargaining agreements reached between each district and its teachers union prior to 2011 remained valid until their expiration, and districts had been on different negotiation calendars starting from several years prior to Act 10. As a result, the timing of expiration was staggered across districts for reasons that were effectively random. This variation creates an opportunity to examine the impact of the end of collective bargaining over teacher pay.

Districts were free under Act 10 to decide whether and to what extent to use their newly gained flexibility to depart from salaries based only on seniority and academic credentials. To characterize these choices, I analyzed districts’ post-Act 10 employee handbooks, documents which list the duties and rights of all teachers and describe how they are paid. As of 2015, approximately half of all districts still included a salary schedule in their handbook and did not mention any other bonuses or increments; I call these seniority-pay districts. The remaining districts, on the other hand, did not list any schedule and often clearly stated that individual pay would be set as the district saw fit; I call these flexible-pay districts.

Using employment records on all public-school teachers in Wisconsin linked to individual student information on achievement and demographics from the Wisconsin Department of Public Instruction, I first document how teacher salaries changed in flexible-pay and seniority-pay districts in the aftermath of the reform. After the expiration of districts’ collective bargaining agreements, salary differences among teachers with similar seniority and credentials emerged in flexible-pay districts, but not in seniority-pay districts. Before the passage of Act 10, such teachers would have been paid the same. These newly emerging differences are related to teachers’ effectiveness: Teachers with higher value-added (individual contributions to the growth in student achievement, as measured by standardized test scores) started earning more in flexible-pay districts. This finding is striking considering that school districts in Wisconsin neither calculate value-added nor use it to make any human-resources decisions. School and district administrators appear to be able to identify an effective teacher when they see one.

Does Flexible Pay Attract Better Teachers?

Changes in teachers’ pay arrangements after the expiration of the collective bargaining agreements changed teachers’ incentives to stay in their district or to move, depending on the teachers’ effectiveness and the pay plan in place in their district of origin. Because flexible-pay districts compensate teachers for their effectiveness and seniority-pay districts only reward them for seniority and academic credentials, teachers with higher effectiveness should want to move to flexible-pay districts, whereas teachers with lower effectiveness and higher seniority should want to move to seniority-pay districts.

The data confirm these hypotheses. The rate of cross-district movement more than doubled after Act 10, with most moves occurring across districts of different type (flexible-pay vs. seniority-pay). Teachers who moved to a flexible-pay district after a collective bargaining agreement expired were more than a standard deviation more effective, on average, than teachers who moved to the same districts before the expiration; these teachers also had lower seniority and academic credentials and enjoyed a significant pay increase upon moving. The effectiveness of teachers moving to seniority-pay districts, on the other hand, did not change. and these teachers did not experience any change in pay.

In addition to inducing sorting of teachers across districts, Act 10 led some teachers to leave the public school system altogether: The exit rate nearly doubled in the immediate aftermath of the reform, to 9 percent from 5 percent. Again, the characteristics of those who chose to leave differed depending on the pay plan each district chose after its collective bargaining agreement expired. Teachers who left flexible-pay districts were far less effective than those who left seniority-pay districts.

Changes in the composition of movers and leavers after collective bargaining agreements expired produced a 4 percent of a standard deviation increase in ex ante (i.e., measured pre-reform) teacher effectiveness in flexible-pay relative to seniority-pay districts. In flexible-pay districts, the effectiveness of teachers who did not move or leave also increased immediately after the reform, compared with teachers in seniority-pay districts, suggesting that teachers in flexible-pay districts increased their effort (Figure 1). Overall, changes in the composition and effort of the teaching workforce led to a 5 percent of a standard deviation increase in student test scores in flexible-pay districts relative to seniority-pay districts in the five years following the reform.

Taken together, these results suggest that higher pay can be an effective tool to attract and retain talented teachers.

It is worth stressing, though, that part of the gains enjoyed by flexible-pay districts came at the expense of seniority-pay districts, with implications for inequality in the allocation of teachers across students. Whether flexible pay undermines equity depends on which districts adopt flexible pay, which is in turn related to the characteristics of the districts’ students, the pool of teachers they employed pre-reform, and their budgets. For example, to attract its most preferred teachers under flexible pay, a district with a smaller budget and a larger share of economically disadvantaged students may have to pay too high a premium, which it cannot afford. The district may thus decide to stay with seniority pay to at least be able to fill its teaching slots.

In a separate study, Chao Fu, John Stromme, and I use post-Act 10 data from Wisconsin to explore this possibility. We conclude that a switch from rigid to flexible pay (like the one that occurred in Wisconsin after the reform) could reduce disadvantaged students’ access to more effective and therefore in-demand teachers. We also show, however, that properly designed bonus programs that redistribute state funds to districts serving large numbers of disadvantaged students could offset this effect.

More Pay for Male Teachers

An additional caveat for a pay approach that gives districts flexibility over teacher pay is that it may produce wage inequality across teachers with similar effectiveness but different demographic characteristics—for example, men and women. A pay plan that allows employers to adjust workers’ pay at the individual level introduces the opportunity for individual negotiations. However, research suggests that women are often reluctant to negotiate for higher pay, giving an advantage to men and creating or exacerbating gender pay gaps.

To test whether this dynamic emerged among Wisconsin teachers after Act 10, Heather Sarsons and I compare the salaries of male and female teachers with the same demographic profile, with the same seniority and academic credentials, and who teach in the same district, grade, and subject. We make these comparisons before and after the expiration of each district’s post-Act 10 collective bargaining agreement to see how the law affected gender equity. Prior to the passage of Act 10, strict adherence to seniority-based salary schedules meant that there was no gender wage gap among Wisconsin teachers. With the advent of flexible pay, though, a gender gap emerged that penalizes women (Figure 2). While small on average, the gap is larger for younger and less experienced teachers. If this gap were to persist over time, women would lose an entire year’s pay relative to men over the course of a 35-year career.

The gender wage gap associated with flexible pay also differs depending on the gender of school and district leaders. In schools with a female principal or districts with a female superintendent, the gap is virtually zero. In schools and districts run by men, the gap is substantial.

The emergence of a gender wage gap following the introduction of flexible pay suggests that gender differences in teachers’ willingness to bargain or their bargaining ability could be driving part or all of it. To shed light on bargaining’s role, we surveyed all current Wisconsin public school teachers. We asked respondents whether they have ever negotiated their pay or plan to do so in the future. We then asked teachers who declined to negotiate why they chose to do so. We asked those who did bargain whether they believed the negotiation was successful.

Survey responses indicate that women are systematically less likely than men to have negotiated their pay at various points in their careers or to anticipate negotiating in the future. The magnitude of the differences is substantial, suggesting that differences in bargaining could lead to a gender wage gap as large as 12%. In line with our wage results, gender differences in negotiating behavior are entirely driven by men being more likely to bargain under a male superintendent, whereas men and women who work under a female superintendent are equally likely to negotiate their salaries. When asked why they did not negotiate, women are 31% more likely than men to report that they do not feel comfortable negotiating pay. Differences in the perceived returns to bargaining and beliefs about one’s teaching ability do not explain why women are less likely to negotiate.

In short, our survey data point to gender differences in bargaining as a likely determinant of the gender wage gap. We also test for, and rule out, three additional explanations. The first is the possibility of gender differences in teaching quality: As districts use wage flexibility to pay higher salaries to more effective teachers, a gender gap could emerge if men are better teachers than women. Our data do not support this hypothesis: women’s value-added is slightly higher than men’s and controlling for it does not affect the gap. Furthermore, the returns to having high value-added after the introduction of flexible pay are positive for men, but not for women. A second possible explanation is job mobility. If women are less likely than men to move, they might be unable to take advantage of outside offers with higher pay. In our data, however, women are as likely as men to move. The third possible explanation is higher demand for male teachers from certain schools, for example those employing fewer men, those that lost male teachers immediately before Act 10, and those enrolling a higher share of male students. While the gender wage gap is larger in such schools, these differences only explain a very small portion of the total gap. Taken together, our results highlight how flexible pay, while possibly beneficial to attract effective teachers and incentivize all teachers to exert more effort, can be detrimental for some subgroups.

How Much Do Teachers Value their Pensions?

To date, most of the debate on how to design teacher pay to improve selection and retention has focused on salaries—that is, the compensation that teachers receive while active in the labor force. Yet, almost all U.S. public school teachers receive a large portion of their lifetime compensation in the form of defined-benefit retirement pensions.

Pension benefits are typically calculated using a formula that multiplies years of service, average salary over the final several years of the teacher’s career, and a “replacement factor” (e.g., 2.5 percent). On one hand, this makes pensions very generous for career teachers and thus extremely onerous for state budgets, to the point that the pension liabilities of current public-sector employees (approximately half of whom are teachers) were fully funded in only two states in 2018. Reforms to increase the solvency of these plans have thus been debated for years across many states. On the other hand, the use of defined-benefit plans implies that any changes to the structure and growth of teachers’ pay—especially towards the end of the career—would translate into changes in pension benefits.

To fully appreciate how salaries and pension reforms would affect the composition of the teaching workforce, it is crucial to understand how teachers value higher salaries vis à vis generous pensions. The multiple provisions of Act 10, which changed teachers’ salaries and future pension benefits with a staggered timing across districts, also allow me to study this question. First, as mentioned above, the legislation introduced flexible pay across districts after the end of each collective bargaining agreement. For the subsample of teachers already eligible to retire (those who are at least 55 years old and have at least five years of service), who enjoyed the most generous salaries before Act 10 because of salary schedules that rewarded seniority, this led to a 7.5 percent decline in gross salaries. Importantly, since pension benefits are calculated using a defined-benefit formula, this decline also translated into a 5.8 percent decline in future pension benefits for the average retirement-eligible teacher.

Second, Act 10 raised employees’ contributions to their pension plan from zero to approximately 6 percent of annual salaries, lowering employer contributions by the same amount (so that the total per worker contribution remained the same). Akin to the levy of a payroll tax, his provision lowered net salaries for all teachers and took place starting from 2012 in all districts.

To estimate the impact of these changes in compensation on teachers’ decisions about whether to remain in the classroom, I track teacher retirement rates across districts as these two provisions of the reform went into effect. Overall, retirement (defined as the share of teachers eligible to claim a pension, which in Wisconsin are those aged 55 and above with 5 or more years of service, who leave at the end of the year) rose to 34% from 15% after Act 10. The staggered timing of the changes’ implementation allows me to separate responses to changes in net salaries (due to the increase in contribution rates) from responses to changes in gross salaries and pension benefits (due to the introduction of flexible pay). I find that approximately 45% of the increase in retirement can be attributed to the decline in net salaries, whereas 55% can be ascribed to the fall in gross salaries and pension benefits.

Next, I test whether teachers’ response to a decline in salaries is equivalent to their response to the same decline in pension benefits, or if teachers instead react more strongly to changes in either form of compensation (which would be consistent with them having stronger preferences for it). The data reveal that teachers respond more to changes in current salaries than they do to equivalent changes in the value of their future pension benefits. This finding has an important implication for the design of teachers’ compensation schemes: shifting part of their lifetime compensation away from retirement towards employment (i.e., raising salaries and making pensions less generous) could significantly improve teacher retention.

Act 10’s Lessons

In sum, Act 10 offered a unique opportunity to understand what would happen to the teacher labor market if it were to become more similar to “standard” labor markets in terms of pay. This reform is still relatively recent; its long-run effects on the public education system in Wisconsin remain to be seen. In particular, careful study of its effects on the selection of new teachers and entry in the profession represents an important avenue for future research.

Taken together, however, the results of the studies conducted to date highlight how reforms of the structure of teachers’ pay can be a powerful instrument to attract and retain effective educators, which could have profound and long-lasting effects on students. Giving school districts autonomy over the design of pay and limiting the rigidity embedded in the use of seniority-based salary schedules can help administrators attract more effective teachers from other school districts—and, presumably, from outside of education. Yet, some of the findings call for caution when re-designing teachers’ pay arrangements: Flexibility can generate inequities across students in the effectiveness of their teachers, and across male and female teachers in the pay they receive.

Barbara Biasi is an Assistant Professor at Yale SOM and a Visiting Assistant Professor at the Einaudi Institute for Economics and Finance. She is also a Faculty Research Fellow at NBER and a Research Affiliate at CEPR and CESifo.

The post Wisconsin’s Act 10, Flexible Pay, and the Impact on Teacher Labor Markets appeared first on Education Next.

Apprenticeships on the Rise

Patrick O’Donnell — Tue, 18 Apr 2023 09:00:55 +0000

Colin Dean (left) was in high school when he started an apprenticeship as a coder through CareerWise at Angi Leads, a home service company. His supervisor was Sheldon Fitzpatrick (right).

Lakshmi Balasubramaniam had tried to launch her career by the traditional route. It just wasn’t working the way she wanted.

Balasubramaniam, 25, went to college just like you’re supposed to and earned a degree in industrial management from the University of Cincinnati in 2019. But she spun her wheels for two years in retail and call-center jobs with low pay and little opportunity for advancement.

Then a family friend told her of an emerging path for moving ahead—a reimagined and condensed form of apprenticeship that would let her pursue her interest in technology, train for a job, and get paid while doing so.

Early in 2022, she started a cybersecurity apprenticeship that gave her three months of training and then placed her in an information technology job with added support for a year. She hopes her training and that year of experience will prepare her to land a full-time job at that company.

The appeal of the apprenticeship was that it offered both pre-service and on-the-job training. “It really sparked my interest,” Balasubramaniam said, “because it would give me what I needed to be successful. Then I will be able to go on and do what I love.”

Apprenticeships that enable young people to learn job skills while working and drawing a salary are nothing new in Europe, where they are a respected and common path to careers in many fields. There, they sometimes take the place of college in preparing students for well-paying jobs, or they may serve as a steppingstone to advanced university training. They can even launch workers on a path to running large companies.

In the United States, though, apprenticeships have traditionally centered on construction trades such as carpentry and plumbing, and they are run through unions rather than by companies, as in Europe. They are viewed as paths to blue-collar jobs, and students who are looking to build a white-collar and well-paying career often choose college instead.

But that’s changing. With college-loan debt making many rethink the country’s college-for-all mindset, apprenticeships are becoming more attractive. Apprentices can earn a paycheck while they train, sometimes even acquiring an associate degree on company time and on the company’s dime. And apprentices can earn middle-class wages without incurring the loan debt that hobbles the finances of many college goers through their 20s and even 30s.

Before the pandemic, the number of people starting apprenticeships had more than doubled over the previous 10 years. That progress stalled during Covid’s height, but data for 2021, the most recent available, show that apprenticeship starts had rebounded to near the 2019 peak (see Figure 1).

Even more important, apprenticeship programs have sprouted across the country in fields such as manufacturing, insurance, and banking as well as in technical fields such as cybersecurity, software engineering, and digital marketing. Before the pandemic, new apprenticeships in non-construction fields had risen to 41 percent of all apprenticeship starts in 2019, from 26 percent in 1999 (see Figure 2), as reported through the Registered Apprenticeship Partners Information Database System. (These percentages capture about two-thirds of all apprenticeship starts in the country, since most but not all states use this system to manage information on their respective apprenticeship programs.)

The style and length of apprenticeships is also changing. Some of these new apprenticeships are adapting traditional European models, in which companies hire and train their apprentices, who also attend school part time.

But some are using variations of a new approach, cast as “hire-train-deploy” by one key player, in which third-party intermediaries make apprentices their “product.” These intermediary companies, both for-profit and nonprofit, have sprouted up in recent years to recruit, train, and match employees such as Balasubramaniam with other firms for a commission, functioning somewhat like a temp agency.

Ryan Craig of Achieve Partners advocates for apprenticeships as an alternative to college.

It’s a lighter, shallower, faster approach than those taken by typical European apprenticeships that last three years or more, or the traditional apprenticeships in the United States that span about four years. They also differ sharply from European apprenticeships by having the intermediary—not the end company—hire the apprentice at the start.

“Hire-train-deploy is the apotheosis of apprenticeship,” said Ryan Craig, who coined the term and founded Achieve Partners, a New York investment firm that has become a major player in the field. It’s a model that allows clients to “try before they buy,” he said. “That matters a great deal to skittish companies.”

The rise in apprenticeships and the variety of fields and approaches is encouraging to Robert Lerman, a researcher for the Urban Institute and co-founder, with Craig, of Apprenticeships for America, a national organization that promotes this form of training while working.

Lerman’s goal: develop standards for learning and a way to make apprenticeships affordable for companies. Training and paying recruits at the same time is expensive, he and other advocates note. And financial aid for work-based learning in the United States doesn’t come close to what is available for college study.

That could change in the next few years, as advocates have already started proposing ways to use more federal tax dollars to support training and apprenticeships, either through new taxes or by changing rules for existing funds. But while there is agreement on both sides of the Congressional aisle that apprenticeships should expand, there’s no consensus on exactly how to make that happen.

Apprentices need to earn valuable skills, but they don’t want to get locked into one company for life. At the same time, employers need assurances that investing in an apprentice will pay off and that they won’t simply be training employees for their competitors. And there’s debate over how much control the government should have over apprenticeship programs and how much should be left to individuals and industry.

If the right balance can be found, Lerman thinks apprenticeships could be a good fit for 25 percent to 30 percent of young people in the United States. That would be a dramatic increase over the 1 percent of youth and young adults estimated in 2018 to be embarking on apprenticeships after high school. It would also put the United States in the same ballpark as worldwide leaders such as Germany and Austria, where an estimated 33 percent of young people participate in apprenticeships.

“I strongly believe that the United States could bring apprenticeship to scale,” Lerman said.

Noel Ginsburg, the founder of CareerWise, likens the costs incurred to recruit and retain employees to a “tax” that can be reduced if companies invest more in training.

Apprenticeships in Flux

The rise of third-party intermediaries and the new hire-train-deploy form of apprenticeship constitute perhaps the most striking developments in a field that is working through several major transitions at once. As the world emerges from the Covid-19 pandemic, a significant reshaping of the job and training market is taking place. And interest in non-college (read: no-debt) career training is surging as loan burdens overwhelm not only many recent graduates but especially young people who start college, take on debt, and don’t finish a degree.

Though most research still indicates that, in general, a bachelor’s degree leads to better outcomes than technical training over the long term, other researchers such as those at Georgetown University’s Center on Education and the Workforce have shown that many “good jobs” don’t need a four-year degree. In some new apprentice programs, participants earn an associate degree from a community college. Anthony Carnevale, the center’s director, is among those who support making such degrees part of free public education.

In this context, European-style apprentice programs are growing across the United States, while youth apprenticeships—those that start during the high school years—are gaining attention and expanding.

The post-secondary apprentice program that the German American Chamber of Commerce of the Midwest started in five Illinois companies in 2015 now operates in nine states: Georgia, Illinois, Indiana, Minnesota, Missouri, Nebraska, Ohio, Texas, and Wisconsin. It also has a sister program in Michigan.

This model focusing on advanced manufacturing has apprentices splitting time between the company and the local community college, with the company paying tuition and apprentices ideally earning an associate degree along with industry credentials.

As of summer 2022, the program had more than 190 active apprentices, the chamber reports.

Swiss-inspired CareerWise, which started in Colorado in 2017, has about 400 high school juniors each year starting three-year apprenticeships in four states plus Washington, D.C. This past fall, it launched in Buffalo, New York, and announced major growth plans in New York City with support from the CEOs of JP Morgan Chase and Accenture.

The German American Chamber of Commerce and CreerWise are leading pioneers in the move to make apprenticeships in the United States a cost-effective talent pipeline and not just a community relations strategy for companies. Both organizations say they bring a real return on investment to companies, even without the federal aid some are clamoring for.

Mario Kratsch, vice president of the German American Chamber of Commerce’s Midwest branch, said apprentices may cost a company money at first, but firms in his network say they start seeing some returns in year two and large ones in year three. Kratsch also reminds companies that they already incur costs when they recruit workers or lose production time because of employee vacations or staffing problems.

“Usually it’s eye-opening to see how much money they currently spend just to keep up with the status quo,” he said. “You’re throwing money out the window. If you add a little bit, a little tiny portion of that . . . in starting an apprenticeship program, then this will help you reduce that amount that you spend to keep up.”

Noel Ginsburg, who founded CareerWise and also serves on the U.S. Department of Labor’s Advisory Committee on Appren-ticeships, said those costs amount to a “built-in tax that’s invisible to business” but that should be weighed as the country debates how to invest in the workforce going forward.

“That tax,” he said, “is caused by employees coming in without the skills they need to be productive” and yet swelling the payroll. He said this hidden “tax” far exceeds any actual training tax that might be considered, “but we’re just used to it. So if you’re actually going to compete globally, you’ve got to fix that problem.”

Some companies express concern that they could invest in training a worker for three years only to see them take those credentials to a competitor. Kratsch counters that companies should instead think about what happens if they don’t train employees and these ill-prepared workers stick around.

And he said companies gain an advantage by recruiting talented people while they’re young and building a company and culture that make employees want to stay.

The poaching problem is less of a worry in Europe than here, Kratsch and others say, because so many European companies train apprentices that there is a greater talent pool to hire from. But the German adaptation here calls for people to commit to staying two years after they complete their apprenticeships—much the way the U.S. military academies do—so that employers have time to see the benefits of their investment.

A New Model Emerges

A new and growing 15-month model has its roots in Britain. Apprenticeships there have increased 500 percent since the 1990s, largely by having third-party intermediaries do the training, which is funded by tax revenue. This growth has come mostly in the fields of business, health care, and commerce, not the traditional skilled trades. Technology apprenticeships have also increased lately.

In the traditional European model, a government body or other legally designated organization serves as the bridge between schools and employers to align teaching with industry needs and help ensure that skills fit the common requirements of a sector.

In Germany, for example, the chamber of commerce fills that role, even creating and administering exams for career credentials. In the Netherlands, a collaborative organization for vocational education known as SBB has legal power to drive cooperation between business and schools.

In England, third-party trainers and organizing companies grew dramatically as funding shifted in the 1990s, letting many and often specialized options sprout from the ground up without the centralized and top-down structure seen on the continent. This new model is starting to take hold in the United States, particularly for tech credentials.

Apprenti, a Seattle-based nonprofit intermediary, is one of the leaders in the short-term tech apprenticeship arena. It started in 2015 as part of the Washington Technology Industry Association, a group with board members from Amazon, Microsoft, and Salesforce, as a way to train people for technology jobs. Apprenti now reports taking on apprentices in 27 states.

Lakshmi Balasubramaniam in Ohio is one of these apprentices. Her apprenticeship, which typifies the emerging model, began in January 2022 with a 13-week coding boot camp funded by Apprenti. The organization paid her $15 an hour as a full-time employee. She then started working in cybersecurity and quality assurance at $24 an hour for Great American Insurance Group in Cincinnati, still as an Apprenti employee; Great American pays Apprenti a higher rate for her service.

Balasubramaniam hopes Great American will keep her on when she finishes.

“I definitely want to continue on after I finish,” she said. “They have mentioned really liking the work that I’m doing, so I am very hopeful for that.”

In recent years, other companies have started seeking to make profits as intermediaries. Multiverse, a British company founded in 2016 by Euan Blair (son of former Prime Minister Tony Blair) expanded into the United States in 2020. The company says it is now running apprenticeships in technology and business skills for more than 40 U.S. companies and 500 firms worldwide, with Google, American Express, and Verizon among those publicly advertising these opportunities.

Blair said that colleges are not properly preparing people for jobs, and companies don’t typically have the ability to train new employees. That’s where apprenticeships come in.

“We really suffer if we decide that academic credentials are the pinnacle, without any good evidence to support them being at all useful or correlative to anything in the labor market,” Blair said.

In New York, Achieve Partners has been buying up training companies across the country to add to its portfolio and promote career training that bypasses college.

Euan Blair founded Multiverse as an intermediary to recruit, train, and match skilled apprentices to companies like Google and American Express.

Achieve Partners’s Ryan Craig, author of two books about the limits of college in job preparation and an upcoming one, Apprentice Nation, said many young people are looking for training that doesn’t demand the investment of time and money that college does. Craig, like Blair, said that companies have a real need for employees who can do the job now, not a year or more down the line, and they don’t have the staff or facilities to offer serious training. Companies like those in his portfolio can fill that need.

“The lesson we’ve learned from looking internationally as well as in the U.S. is that every economy and every sector where apprenticeships proliferate, it’s because there are high-intervention intermediaries who do most or all of the heavy lifting for employers,” Craig said. “We don’t have that here, outside the construction trades.”

In some cases, the intermediary can be a chamber of commerce or local sector partnership. In Cleveland, Ohio, manufacturing organizations banded together to organize a small apprentice program that is still sorting out the cost and length that will be attractive to employers. On a parallel track, the chamber of commerce there, the Greater Cleveland Partnership, has worked with its local information-technology sector partnership to start an apprentice program in that field.

Even then, the chamber linked with Apprenti and with another company, Interapt, to connect apprentices with private trainers and navigate federal and state registration and laws.

It’s not an easy task, said Kratsch. German companies with Illinois factories approached the chamber for help in navigating labor law, meeting standards for German credentials for apprentices, and setting up partnerships with community colleges to provide the technical training in advanced manufacturing the companies needed. The chamber even runs “train the trainer” sessions so company staff know how to teach apprentices.

Challenges and Costs of Lite Apprenticeships

Jennifer Carlson, co-founder and executive director of Apprenti, said she tried to follow the lead of Germany and Finland in developing Apprenti’s plan but had to make concessions to employers who balked at spending money on three, four, or five years of training.

“The U.S. system was just simply not in place to think through a four- or a five-year apprenticeship model when it came to technology roles,” Carlson said. “I do think that it will get there down the road, but near-term, the companies that we were working with wanted it bigger, better, faster. And so we accelerated the training and compressed the front end, and then they get people on the job.”

That has a drawback, she said. Apprenti’s staff have observed that, with short-term apprenticeships, workers end up needing to level up their skills before long. They need “pieces that probably would have been incorporated if we had gotten a company to agree to a three- or a four-year apprenticeship where there had been additional training,” Carlson said. “We kind of had to take a big step backwards to even get any kind of adoption in the U.S.”

Kratsch said the impatience of employers is more of a challenge here than it is in Germany.

“It’s really hard to have a company committing to a mid- to long-term strategy and following that strategy in the United States,” he said. “The cycles are pretty much very short. In Germany those companies have a strategy we’re looking at, like, ‘How many people do we need in the next 10 to 15 years in which position?’ and that’s when they start right now preparing those people to fill those positions.”
The limits of the quicker apprenticeships have drawn concerns from experts looking at England, too, suggesting that the model needs work. An assessment of apprenticeships there by the Organisation for Economic Cooperation and Development in 2018 praised the growth of training but highlighted worries.

“There is still a long way to go to establish an apprenticeship system in England to match those of the strongest countries,” the report states. “A large proportion of apprenticeships in England still involve low-level skills, acquired in a period of little more than a year, with a limited component of general education, and with most of the training taking place off the job. Work-based learning is under-developed.”

But even the shorter apprenticeships take a substantial investment. Companies pay apprentices as full-time employees for the hours they work and often while they are attending school, too. Any needed additional training—termed “related technical instruction”—adds significant costs, whether done by the company itself, yet another training company, or a community college.

In Europe, publicly funded schools work with industry to do that training as a public service, letting companies there avoid costs U.S. companies would have to pay themselves.

Oren Cass has called for designating half of government aid earmarked for higher education to a workforce training fund for employers to recruit and train their own apprentices.

Public Funding Options

Free community college, in line with Carnevale’s call to better prepare students for work by offering 14 publicly funded years of school instead of 12, could take the cost of related technical instruction off the table.

Some have proposed extending the federal college Pell Grants to more non-degree training programs or to part-time students who work and go to school at the same time. Others want to create a separate fund to reimburse businesses for those costs instead of giving direct aid to students.

Oren Cass, formerly of the Manhattan Institute and founder of American Compass, a declared advocate for conservative economics, has been calling the last few years for reallocating some federal support for colleges into a workforce training grant fund that would pay employers up to $10,000 a year to train employees while they work. Cass proposes gradually shifting about half of the $200 million in annual federal and state higher-education aid to these training funds.

He said that giving employers money to pay for apprenticeship training is a better way to spend public money than letting students decide how to use it. Students, he said, often guess at which courses and degrees will be the most useful, but many of them choose unwisely, and colleges too often are paid for students taking classes that don’t prepare them for what employers need.

Letting employers decide on what training is appropriate, he said, is a “neutral approach” that would compel colleges to treat employers as their customers.

“Their success would depend on offering programs that appeal to employers’ needs,” Cass wrote. “The employer would likewise have a greater incentive to engage with the community college in designing a relevant and integrated program of study. In other cases, employers might operate training programs themselves or through industry associations or union partnerships.”

Senator Tom Cotton, an Arkansas Republican, incorporated much of Cass’s plan into bills he introduced in 2021 and 2022, hoping to establish funding for such a program. Instead of using federal money for colleges, Cotton proposed, the government could levy a 1 percent tax on large private university endowments, those exceeding $2.5 billion, with a few other restrictions.

He said the country needs to stop “propping up bloated colleges that serve—often poorly—a minority of our citizens.”

Neither the 2021 nor the 2022 versions of the bill had a hearing in the Democrat-controlled Senate Finance Committee. Originally called the Ivory Tower Tax Act in 2021 before being recast, with more detail about the grant program, as the American Workforce Act in 2022, the bill targets the wealthiest universities, such as Harvard, Yale, Princeton, and Stanford. That strategy has cost the proposal support and distracted attention from the core idea of awarding training grants to industry.

Carlson, while not familiar with Cotton’s proposal, said she agrees support is needed to offset the $8,000 to $15,000 per person that Apprenti spends on initial training. And Skillstorm, a training company that works with Achieve Partners, reports similar costs: $15,000 for upfront training, $12,000 for three months’ salary during training, and $3,000 to $5,000 to recruit and hire apprentices.

There’s also a push to change the way existing aid for apprentice programs is handled. Too much of that aid is distributed by states and local workforce-development boards under the Workforce Innovation and Opportunity Act, Carlson said. That’s a challenge for multi-state programs such as Apprenti, because each board is a silo with different requirements and eligibility rules, and each program typically only funds training in its own geographic area.

“The challenge for any intermediary in any sector is that no two workforce-development boards implement the money the same way,” she said. “Right now, I braid 11 different sources of funding, and I’ll tell you, it’s a royal pain.”

Tal Frankfurt is founder of Cloud4Good, a new intermediary in Asheville, North Carolina, that is running apprenticeships in using the Salesforce management software. Frankfurt had similar complaints about the lack of central funding.

“My 30 apprentices are spread across probably 15 different states,” he said. “So, because we’re a remote environment, these grants don’t apply. For me to actually go and chase the grants, I have to chase 15 different workforce boards. That model around funding apprenticeship doesn’t really apply to the 21st century, when people are working remote.”

The Workforce Innovation and Opportunity Act, which the House tried to reauthorize last year without gaining Senate support, will be on the agenda for an update again this year—only in a House that has switched to a Republican majority. North Carolina Representative Virginia Foxx, the new chair of the House Committee on Education and the Workforce, has said she wants the law changed so businesses have more say in how training money is spent.

She would restore federal recognition and funding for the Industry-Recognized Apprenticeship Program, which was created under President Donald Trump but scaled way back under President Joe Biden. This program gave businesses more authority to design apprenticeships—and pay scales—as they saw fit, but Democrats and labor groups objected to the lower levels of skills and pay such apprenticeships allowed.

A Foxx spokesperson said that legislation has already been filed to bring back the program and that Biden’s move was “deeply misguided and took away a valuable tool to end the college-for-all mentality and offer Americans faster pathways into good-paying jobs.”

Lerman and Craig also want the federal government to help out. Lerman’s plan for expanding apprenticeships—which would resolve some complaints about the Industry-Recognized Apprenticeship Program by including clearer standards about which skills industry should teach to apprentices—would set aside $4 billion a year for $4,000 bonuses to intermediaries or others to create a million new apprenticeships each year.

England passed an apprenticeship tax in 2017 to encourage businesses to start apprenticeships. It’s a use-it-or-lose-it incentive: Large companies are taxed an extra 0.5 percent of their payroll but can recover the money if they spend it on apprenticeships.

That tax, though, has caused controversy and brought a reduction in apprenticeship starts, not the desired increase, even before the pandemic stifled efforts. And some critics say much of the money is essentially paying for training that would have happened anyway.

There are also moves to streamline federal registration of apprenticeships and improve the reward to companies for registering. The bureaucratic burden on companies, with little perceived reward, is partly why the Industry-Recognized Apprenticeship Program was started. The Advisory Commission on Apprenticeships, appointed by then U.S. Secretary of Labor Martin Walsh in late 2021, will present its final report this year on how to modernize them. The commission is also looking at ways to improve youth apprenticeships, those that start during high school.

The commission might also have a plan for funding apprenticeships. CareerWise founder Ginsburg, who is a co-chair of the commission, said he could support tax credits or an apprenticeship tax similar to England’s. But neither he nor the commission have proposed any tax rates or rules or presented any calculations on how much money a tax might raise.

Multiverse’s Blair, though, said he would love tax help but doesn’t need it. Some companies tried to create apprenticeships because of the tax, he said, but two other factors—the lack of capacity to train new workers and a desire to build a more-diverse workforce—drove more customers to him than the tax did.

“Given you can solve those two things in tandem with an apprenticeship, it makes commercial sense for employers.” he said. “So you don’t need a government incentive.”

He added, though, “Of course, anything government can do helps, because at the moment, in the U.S., the market is still learning about this apprenticeship concept, right?”

Patrick O’Donnell is a reporter in Cleveland, Ohio, who has studied career training as a fellow for the Institute for Citizens and Scholars and as a Spencer Education Reporting fellow with Columbia University’s Graduate School of Journalism.

The post Apprenticeships on the Rise appeared first on Education Next.

Beyond the Big Yellow Bus

Michael B. Horn — Tue, 11 Apr 2023 09:00:05 +0000

HopSkipDrive offers an innovative alternative in transporting students to and from school.

Just as there’s no one-size-fits-all way to educate students, perhaps there’s no one-size-fits-all-way to get them to school either.

That’s the argument behind HopSkipDrive, a startup that is seeking to complement and redefine the traditional bus model of taking students to school. Instead of kids making their way to the pre-determined route of a 72-passenger school bus, HopSkipDrive creates customized pick-ups in cars and vans based on individual students’ needs. It’s a rideshare-like model with similarities to and major differences from Uber and Lyft.

The company provides an app that connects families and students with highly vetted drivers, all of whom are also experienced caregivers who either currently have a child at home or have cared for children in the past. They use their personal, pre-approved cars to drive students to and from school or after-school activities, while families and the contracting agency—such as a school, welfare office, or group home—can track the car’s movement in real time. Rides are scheduled well in advance but can be changed with a few hours’ notice.

When three parents launched the app in 2015, “it had nothing to do with school transportation,” said Chief Executive Officer Joanna McFarland, a cofounder and mother of two. “It really had to do with creating options for full-time working moms and families like mine, who were really struggling to just make the logistics of running a family work.”

But safely transporting kids turned out to be a widely shared challenge. Today, Los Angeles-based HopSkipDrive contracts with schools, districts, counties, and nonprofit partners in eight states and Washington, D.C., with a focus on meeting the transportation needs of students who fall outside traditional school-bus norms.

A Widespread Problem

The initial idea for HopSkipDrive was hatched at a child’s birthday party, and the original intended market was parents like McFarland and her cofounders, who wanted to get their kids to after-school activities safely without interrupting their own workdays. But company leaders soon realized there was a broader need for more flexible student transportation options, fueled by phenomena such as open enrollment within districts, students attending out-of-neighborhood “choice” schools, the less-predictable needs of students experiencing homelessness, and varied start times within districts. Within about two years, HopSkipDrive started to work with counties and school boards that were struggling to meet transportation needs because of a growing shortage of bus drivers.

After the abrupt closure and eventual reopening of schools due to Covid-19, those shortages grew more severe. Many districts initially furloughed drivers during school-building closures, and many of those drivers did not return to the job after schools reopened. A 2021 survey by the National Association for Pupil Transportation found that every region of the country was experiencing driver shortages, and at least two-thirds of districts had altered service as a result. Some 51 percent of respondents described shortages as “desperate.”

With fewer school-bus drivers, districts have consolidated routes and lack back-up options when a driver calls out sick. Some districts in Georgia cut bus service for students attending charter schools or schools of choice. Service gaps have caused many students to arrive late or miss school if their parents and neighbors are unable to carpool on the fly. Some state and district leaders have gotten creative in their responses to the problem: Massachusetts called on National Guard troops to drive students, and Washington, D.C., launched a free school-bus driver training program for city cab drivers.

HopSkipDrive, which initially laid off much of its staff and launched an adult ride option during the pandemic, proved another ready solution—and one that had been designed by parents with children and family needs in mind.

“Caregivers on Wheels”

HopSkipDrive rides are performed by what the company calls “CareDrivers”—adults who are vetted both for their experience with children and driving abilities. CareDrivers must have five years of caregiving experience as parents, guardians, nannies, teachers or paraprofessionals, or in other childcare roles. They submit to a 15-point certification process, which includes a fingerprint-based background check, motor vehicle history search, and ongoing monitoring for new driving infractions. The driver must use a vehicle that is less than 10 years old and seats four to seven passengers. New drivers go through a live orientation with a member of the HopSkipDrive team.

Joanna McFarland, a cofounder of HopSkipDrive, wanted a more flexible option in school transportation.

The company facilitated more than 400,000 rides for children and families in 2021, with a group of more than 4,000 active CareDrivers serving about 350 school districts. Over 2 million children have been driven safely over the company’s brief history. These rides totaled more than 7 million miles in 2021, and 99.7% concluded without a safety-related issue. In all, HopSkipDrive rides have traveled more than 20 million miles to date, with no critical safety incidents.

The company keeps close watch on drivers during rides. Using telematics—the long-distance transmission of digital data—HopSkipDrive tracks the whereabouts of drivers and children. It also checks for unsafe driving behaviors by monitoring phone usage, speeding, acceleration, hard braking, and hard turning. This technology provides visibility without installing in-vehicle cameras, which pose privacy concerns. In addition, the company also provides districts and parents with backup drivers in case of a last-minute cancellation, as well as real-time location updates.

Other innovators in this space use similar driver vetting and real-time location tracking via apps, but with different focuses. For example, Zum contracts with schools and districts to modernize routes and fleets, enhance efficiency, and provide carbon-neutral transportation in cities such as Los Angeles, San Francisco, and Seattle. TaxiMom offers a subscription-based transportation service for families in the Dallas-Fort Worth and Houston markets.

Part of the Transportation Puzzle

HopSkipDrive is not looking to replace the school bus. In a densely populated area, filling a 72-passenger bus is still the most efficient way to get students to school. Facilitated ridesharing is instead one part of a more comprehensive transportation solution for school districts, two-thirds of which own their fleet of buses.

But the company does look like a disruptive innovation relative to the school bus. It is bringing a more affordable and customizable technology-based solution that isn’t as good as the status quo, judging by historical measures of performance, to non-consumers for whom the alternative is nothing at all. In this case, HopSkipDrive is using technology to reach students who previously had no district-provided ride or who were over-served by a large school bus in a lightly populated area.

For example, one of HopSkipDrive’s larger partnerships is with the Aurora Public Schools in Colorado. The district uses HopSkipDrive to provide school transportation for about 70 students who are experiencing homelessness, are in foster care, or have special needs or disabilities that make riding a school bus challenging.

“These are kids who don’t fit neatly on a school bus route or kids who are highly mobile and moving frequently,” McFarland said. “If you are a child in the foster system who moves placements at 10:30 at night, you can’t reroute a school bus to get that child to school. And yet HopSkipDrive can get them to school the next day with no change in schooling. And we know that every time a child moves—and the average child in foster care might move three to five times a year—that might mean switching schools. Credits don’t transfer. It can take several weeks to change schools. What one district teaches in fourth grade, another district teaches in fifth grade… We have federal mandates to fix that, but transportation is one of the biggest barriers. And a service like HopSkipDrive really helps districts provide transportation for those hardest-to-serve students in a really flexible way.”

At Rocky Mountain Prep, a charter school in Colorado, the arrangement works differently. There, HopSkipDrive helps specific students who are struggling to get to school, buying time for the school and families to develop longer-term solutions to the attendance challenge. In one instance, Rocky Mountain Prep provided HopSkipDrive to a parent who had recently given birth to help get her older child to school for a few weeks.

HopSkipDrive may also lead to better optimization of school transportation in the longer run, said McFarland.

“Some of our more innovative districts are really starting to think in a much more holistic way, and we are helping them really think about: ‘What does your fleet size need to look like? How many buses do you need? How many drivers do you need?’” she said. “Because we’re operating in this world of shortages, but when you think about it as a utilization problem, maybe the number of bus drivers that we have is actually sufficient. Maybe we can … save money and use that money to increase bus driver salaries and retain drivers.”

Driving into the Future

The question for any transportation innovation now is whether it can scale. Regulation will play a role.

Many states have antiquated regulations around who can drive students to schools, according to McFarland. For example, Massachusetts requires a driver to have a certification that is close to a commercial driver’s license—a rule designed for safety back when a school bus was the only transportation a district would have provided for students to get to school. Similarly, many districts require their own unique background checks for potential drivers, a roadblock for vetted CareDrivers who want to drive for multiple districts.

States are updating their laws, however, to make room for new transportation solutions. A 2021 Maryland law allows districts to transport students in vehicles other than official school buses, and new regulations in Georgia permit the use of “alternative vehicles” for students who receive special-education services, are in foster care, or are experiencing homelessness.

The ultimate solution seems to be to update transportation regulations to focus on outcomes—namely safety and reliability—instead of inputs. That means setting a baseline for safety consistent with different vehicle types and using technology to enforce safety and create accountability.

Looking beyond once-in, once-out traditional school busing will be especially important in states where educational options are proliferating, through charter schools, education savings accounts and micro-grant programs, microschools, and other flexible and innovative schooling arrangements. Today, somewhere between 1.1 and 2.1 million students are enrolled in microschools or learning pods, for example.

But these options aren’t real choices if students don’t have a way to get there.

“We see over and over again, parents would choose a particular school for their kids, but they don’t enroll in that school because it’s across town or it requires two hours on a public bus or they just can’t get their kids there,” McFarland said.

Some states aren’t just modernizing their transportation regulatory framework, they are seeking to spur innovation. The Arizona Transportation Modernization Grants Program, for example, awarded $19 million in its first year to 24 schools and nonprofit education agencies with novel transportation solutions. That included the Black Mothers Forum, a nonprofit that operates microschools in Tempe and South Phoenix, which developed a community carpool app and provided transportation for all students. And it included Tolleson Union High School District, which contracted with HopSkipDrive to create a hub-and-spoke model to provide transportation to out-of-district students that want to attend one of its specialized programs.

The models are different, but the goals are the same: Reduce the time in transit for students and get them to their educational options on-time, safely, and ready to learn.

“You might have a bus that is full in the morning but in the afternoon is empty because kids are doing different activities,” McFarland said. “So, when you start to think about that, you can open up so many opportunities both inside and outside the classroom. Just thinking a little bit more holistically and a little bit more creatively.”

Michael Horn is an executive editor of Education Next, co-founder of and a distinguished fellow at the Clayton Christensen Institute for Disruptive Innovation, and author of From Reopen to Reinvent.

The post Beyond the Big Yellow Bus appeared first on Education Next.

“Year of School Choice” Promise Collides with Reality of Litigation-Caused Delays

Nirvi Shah — Tue, 28 Mar 2023 09:00:41 +0000

Ruth, Katie and Alexander Switzer (left to right) plan to benefit from West Virginia’s Hope scholarships after uncertainty and a delay resulting from litigation.

When the West Virginia legislature passed a law in 2021 that would give parents money to pay for private school tuition or other education-related expenses, it got Katie Switzer thinking.

Her oldest child, Alexander, had struggled in preschool. She didn’t think he was ready for kindergarten, even though he would be the right age based on West Virginia’s public school requirements. So she kept him home for a year and applied for the scholarship as soon as she had a chance, hoping a combination of some in-person schooling and working with her son at home would be the ideal fit.

She wanted a scholarship for her oldest daughter, Ruth, too. Ruth turned 5 after the state cutoff for entry into kindergarten. Ruth has apraxia of speech, which can make it hard for her to say what she wants and requires a speech pathologist with specialized skills to help her learn to form words. Switzer has been paying thousands of dollars out of pocket for that speech therapy. She hoped to use the scholarship for some of that therapy while Ruth would learn reading and other lessons at school.

So Switzer applied. She sorted out how to use the money to pay for the lessons she would teach the kids at home, specialized therapy a school couldn’t provide and a la carte classes at school. It was a good plan, she thought.

Until it wasn’t.

West Virginia’s law stood out as a major advancement for school choice when it passed, even in a legislative year school choice advocates generally considered full of victories. The state previously did not have any private school choice programs. Suddenly, it had an option with expansive eligibility for financial help. Essentially every student statewide could apply, and in the long term, it would include students already enrolled in private schools or being homeschooled, even if they had never attended public schools.

While private school enrollment nationwide did tick up with so many public schools closed during the early days of the health crisis, that followed decades of declining enrollment nationwide. Parents have more choice than ever among traditional public schools, charter schools, homeschooling, private schools, and newer models such as pods and microschools, which also took off during the pandemic and which some states have also recognized with legislation.

But was the big promise of school choice realized in West Virginia and other states that were part of the wave of new choice laws ushered in during the pandemic?

The reality is there’s a lag between passing a law and practically implementing it. In West Virginia and elsewhere, at least some of the programs created recently have faced time-consuming legal challenges that prevented students, and parents, from immediately using the choices or money provided.

In West Virginia, scholarships for Switzer’s kids and about 3,000 others who had signed up were delayed for months by a lawsuit. Broad access to Hope Scholarships in West Virginia was one reason the group Public Funds Public Schools sued, said Jessica Levin, the group’s director, who is also a senior attorney at the Education Law Center, another organization that works on public school funding issues. The suit said the new program would violate the state’s constitution in several ways.

“It’s a bold and illegal and very harmful move,” Levin said of West Virginia’s program. “It makes it all the more harmful to public school budgets.”

Public Funds Public Schools has also litigated, with some success, to delay school choice programs in Nevada and Tennessee.

The group sometimes partners with teachers unions on amicus briefs and has represented parents who are teachers, including union leaders, as plaintiffs in some of its lawsuits.

One common element of the cases the group pursues: Public schools must enroll all students, Levin said, while private schools can choose to discriminate based on students’ disabilities, religion or sexual orientation.

“Public schools are cornerstones of democracy,” Levin said, and “every child has a right to public education that is adequately funded to make that right real.”

A lower court in West Virginia agreed with Public Funds Public Schools, putting the program on hold in July 2022. An appeals court declined to lift that hold until an appeal worked its way through the court system. But in October 2022, the state Supreme Court ruled three-to-two in favor of the Hope Scholarship program, reinstating the program.

“I’m so excited,” Switzer said.

Ruth and Alexander spent the fall 2022 term at a public charter school, full-time.

Now, Switzer said the children will use some of their $4,300 each—the amount they would have had for the whole school year had the program not been blocked in the fall—during this spring 2023 semester to attend a two-day-a-week homeschool co-op and use the rest of the money for speech therapy and dyslexia tutoring.

The West Virginia Treasurer’s Office, which oversees the administration of Hope, said all students originally eligible for the program at the start of the 2022-23 school year, about 3,215 children, were able to remain so.

Still, the delay in access to the money came at an actual and emotional cost, Switzer said.

“They both have relationships with teachers and kids in their classrooms, even if the school they attended hasn’t been perfect and couldn’t meet Ruth’s special needs,” she said. In addition, the family has spent $600 a month on Ruth’s specialized speech therapy and another $300 a month for dyslexia-specific tutoring.

“So not having Hope has been very expensive for us,” she said.

* * *

Since the onset of the pandemic, more than 20 states added new private school choice programs or expanded existing ones, mostly during the 2021 legislative session. A few more came along in 2022. But 2023 has seen a surge specifically in the kind of expansive programs that concern Levin’s group. That includes programs in Iowa, Utah and Arkansas. Over the last few years, some states expanded support for charter schools, too, adding financial support for charter school facilities, for example, or making it easier for charters to be authorized. And the surge in the number of kids attending charter schools earlier in the pandemic has held up, according to new data from the National Alliance of Public Charter Schools.

The sheer volume of legislation has been heralded as a sea change in the school choice landscape. In reality, however, said Michael Hartney, a fellow at Stanford University’s Hoover Institution and an assistant professor of political science at Boston College, states that moved the needle on private school choice over the last few years are ones “where they could have gotten things done before the pandemic.”

Overall, despite the gains, he said, “it’s symbolic,” given the relatively tiny share of American students who attend private schools using vouchers, or who use subsidies to pay for tutoring or supplies for homeschooling.

“The basic equilibrium to me seems pretty much unchanged.”

Still, the creation of a voucher program in West Virginia was notable. Teachers had descended on the state capitol repeatedly in 2018 and 2019 to demand better pay and benefits and to push back against proposals supporting charter schools and private school vouchers.

Teacher Wendy Peters, who was one of the plaintiffs in Public Funds Public Schools’ suit against the West Virginia scholarships, was president of her local union in Raleigh County, West Virginia, during those protests.

“It sounds good in theory: Let’s give someone some money,” she said. “I don’t think people realize how devastating it is for the public schools.”

Her son uses special education services, and she doubts any private school would accept him if she chose to use one of the scholarships. For other parents of children with disabilities, they may not realize that their access to special education could evaporate at a private school. “Who’s to say they’re not going to come right back” to public school, Peters said.

“If I took that $4,300 for myself, there is not a private school that would take my son,” she said.

* * *

At times, the pandemic was cited as the reason parents needed more schooling options—with teachers unions taking the blame for keeping school buildings closed and driving lawmakers to create choices outside of traditional public schools.

Yet some of the states that added vouchers or education savings accounts with the potential to encompass large numbers of students, or that made the largest expansions to existing choice options, are right-to-work states with limited union influence, Hartney noted. And in some cases, these same states forced schools to reopen for in-person classes, while also expanding choice.

The major national unions oppose private school choice. At its convention in July 2022, for instance, the American Federation of Teachers resolved to continue condemning “the diversion of public funds to discriminatory voucher programs that significantly reduce public financial support to our cherished public schools,” and said it would lobby against these policies.

In December, with the support of the national AFT and Public Funds Public Schools, the New Hampshire AFT to block the Granite State’s new Education Freedom Accounts.

This expansive program, also created during what’s been called the choice wave in 2021, is in a much different place than West Virginia’s. New Hampshire’s new Education Freedom Accounts became law in June 2021. The legislature anticipated only a few dozen students would sign up during the 2021-22 school year, but by year’s end, it was more than 2,000 kids. More than 3,000 applied for the 2022-23 school year.

The program allows students to use the state portion of their per-student allocation — or $4,857 for the current school year — toward school tuition, tutoring, online schooling, educational supplies, internet access, and similar expenses. The program doesn’t require students to have attended a public school to access the money. The lawsuit says that the biggest beneficiary of the money in 2021 was Amazon, where parents spent nearly a fifth of their EFA dollars.

Parents can combine the money with another school choice program, a longstanding tax credit scholarship program, and newly created grants for all students in the state, including those attending public school, to pay for tutoring and other educational expenses because of disruption from the pandemic. This school year, more than 1,100 students are drawing funds from both EFAs and the tax credit scholarships.

For some parents who were essential workers as schools shifted to remote learning in the spring of 2020, in-person schooling was a necessity, and private schools were their only option in the early days of the Covid-19 crisis, said Kate Baker Demers, whose Children’s Scholarship Fund organization approves applications and distributes the New Hampshire tax credit scholarships and Education Freedom Account money.

“You have to bring your child somewhere if you drive a truck,” Demers said. “If schools were to shut down again, now we have a solution for those families.”

Only about a quarter of students who used one of the new Education Freedom Accounts last school year were “switchers,” or kids leaving their public schools for any reason, Demers said. One enterprising private Christian school leader in Laconia, N.H., encouraged existing students to apply for the grants, and all but two did.

The school choice momentum in New Hampshire has slowed. Lawmakers ended up putting an expansion of the program on hold in 2022. The Education Freedom Accounts were enacted in 2021 by tucking a provision into the state budget bill, rather than passing a standalone piece of legislation.

One 2022 proposal would have expanded eligibility to families at 500 percent of the federal poverty level. Another would have created a voucher that would have come from local school district budgets and would have been worth between $291 and $41,000 per student to use for the same kinds of education expenses as the Education Freedom Accounts.

What did pass was a bill sponsored by state Democrats calling for an audit of the program in 2023. Republican Governor Chris Sununu signed that legislation in July 2022.

The New Hampshire lawsuit says the EFA program violates state law because it is funded via transfers from the state’s Education Trust Fund. “The ETF statute enumerates its permissible uses, which do not include private education or vouchers, and states that the funds are not to be used for any other purpose,” Public Funds Public Schools said. In addition, the lawsuit charges that the accounts law violates a provision of the state constitution requiring all proceeds from the state-run lottery, which are deposited into the trust fund, be used to support public school districts.

* * *

In Indiana, a major expansion of school choice options, enacted in 2021, also took effect last school year, resulting in a surge of interest in private school vouchers in that state. Lawmakers added to the list of who is eligible for a private school choice, including children in foster care and more middle-class families.

The use of private school vouchers in Indiana had plateaued in recent years and actually declined during the 2020-21 school year. Then it jumped by almost 25 percent in 2021-22, after lawmakers expanded who is eligible for the money. Now, a family of four can have a household income of more than $147,000 and access vouchers.

Even as the share of students who can use public dollars for private school grows in Indiana, a report last year found that private school enrollment has declined as the state has created more voucher programs. In 2000, more than 134,000 or 12 percent of Indiana students, attended private schools. As of 2021, fewer than 61,000 or 5.4 percent, did so, Michael J. Hicks and Dagney Faulk of Ball State University found.

“I know much of the rhetoric about school choice claims it is designed to destroy public education,” Hicks wrote in The Herald-Times, based in Bloomington, Indiana. “If so, it has been a colossal failure. Since Indiana began its path to school choice, private school enrollment in the state plummeted by more than half.”

Could that change? Perhaps: Lawmakers this year are considering additional ways to expand access to school choice in the Hoosier state.

* * *

Lawmakers in Arizona also created another expansive choice option in 2022, in a state already awash in such programs.

Every student in the state can use an Empowerment Scholarship Account in Arizona under a law then-Governor Doug Ducey, a Republican, signed in July. That’s more than a million kids. The money can be used for private school tuition, homeschooling, tutoring and other educational services.

A group that forced a ballot referendum on another private school choice bill earlier in Ducey’s tenure, which voters rejected, attempted to do the same with the new law. Had they succeeded, the expansion would have been on a long hold until voters had a chance to weigh in, and that could have been its undoing.

But that petition drive failed to gather enough signatures to push the newest measure to voters.

Now that the far-reaching choice program is a reality, it’s not clear how many former public school parents are using the option, however, though it has proven popular with students already attending private schools. Only a relatively small number of Arizona students used the program until now: a little more than 13,000 students statewide, the Arizona Department of Education said.

The latest figures show about 45,000 Arizona students are using ESA money.

* * *

It’s not always lawsuits or petition drives that delay or alter the course of a choice program. In Ohio in 2020, state lawmakers put on hold plans for an expansion of the state’s EdChoice private school voucher program to students who attended hundreds of public schools considered to be poorly performing.

Parents whose schools were on the list the prior fall prior and who had counted on using a voucher for private school tuition sued the state over the delay. Ultimately, the state legislature changed the voucher program, and not all of the students originally identified as eligible for a voucher had the same option in the long run.

The changes did expand Ohio’s program significantly, but the eligibility rules were altered so that they were now based on family income level rather than public school performance.

Now, a group of more than 200 school districts, including the state’s largest—Columbus City Schools—and parents are suing Ohio over its longstanding private school voucher program. The group, called Vouchers Hurt Ohio, says state spending on vouchers has increased to $350 million during the 2020-21 school year from $42 million in 2008.

In December 2022, a judge ruled the lawsuit can proceed.

More than 20 years ago, the U.S Supreme Court upheld Ohio’s voucher law, which at the time was limited to students in the Cleveland City school district. In the decision about the new lawsuit being allowed to move forward, the judge wrote that the state’s so-called EdChoice program has expanded and changed dramatically even since it went statewide in 2005. Far more families are eligible and there is no limit on how many students can use vouchers.

The suit could affect the more than 50,000 Ohio students who use the program, even as lawmakers hope to expand choice even further in the state.

* * *

Back in West Virginia, Katie Switzer was surprised by Ruth and Alexander’s experience full-time in a public charter school.

Despite the delay in Hope Scholarships, West Virginia did begin the 2022-23 school year with one new form of school choice: Four charter schools opened this school year, said Adam Kissel, chairman of the West Virginia Professional Charter School Board, after a state law allowing charters passed in 2019 survived legal challenges and the first group of schools were authorized to open in fall 2022.

One of those schools is West Virginia Academy in Monongalia County, where the Switzer family lives. Switzer became a regular presence at the school as a volunteer while her kids were enrolled.

There was a time when the scholarships were in legal limbo that she couldn’t picture moving Alexander out of the school. “He’s done really well here,” she said.

Things were more difficult for Ruth, who also has some challenges processing what she hears. After a whole day in a classroom with many people speaking at once, and her own words sometimes slow to form, “she’s exhausted,” Switzer said. Still, she said before the court made its decision, “I have to say she’s getting better every week,” and she felt her daughter had been given an opportunity to do well at the charter school.

Now, it’s time for a shift, no easy feat for many people, and especially young children. It’s one more cost of the Hope Scholarship delay, she said.

“We still have to go through a transition,” Switzer said, “and it’s hard on everyone.”

Nirvi Shah is education enterprise editor at USA Today. This story was produced with support from the Education Writers Association Reporting Fellowship program.

The post “Year of School Choice” Promise Collides with Reality of Litigation-Caused Delays appeared first on Education Next.

To Teach Better Writing, Don’t Ban Artificial Intelligence. Instead, Embrace it.

Michael B. Horn — Wed, 22 Mar 2023 09:00:52 +0000

For all the speculation about ChatGPT’s potential to upend K–12 writing instruction, there has been little investigation into the underlying assumption that the AI chatbot can produce writing that makes the grade.

We put OpenAI’s ChatGPT to the test by asking it to write essays in response to real school curriculum prompts. We then submitted those essays for evaluation. The results show that ChatGPT produces responses that meet or exceed standards across grade levels. This has big implications for schools, which should move with urgency to adjust their practices and learning models to keep pace with the shifting technological landscape.

Background

When it burst onto the scene in November 2022, ChatGPT’s clear and thorough written responses to user-generated prompts sparked widespread discussion. What it might mean for K–12 education was one area of speculation. Some worried about the potential for plagiarism, with students dishonestly passing off computer-generated work as their own creative product. Some viewed that threat as particularly formidable, pointing to three attributes that make ChatGPT different from past tools. First, it generates responses on-demand, meaning that students can receive a complete essay tailored to their prompt in a matter of seconds. Second, it is not repetitive. It tends to answer multiple submissions of the same prompt with responses that are distinct in their arguments and phrasing. And third, its output is untraceable, as it is not stored in any publicly accessible place on the Internet.

Education decision makers are already moving to respond to this new technology. In January, the New York City Department of Education instituted a ban on ChatGPT by blocking access to it on all its devices and networks. Los Angeles, Oakland, Seattle, and Baltimore school districts have imposed similar prohibitions. As leaders in other districts, schools, and classrooms grapple with if, when, and how to make changes in response to this technology, they need a read on how well ChatGPT, in its present form, can deliver on the threat it is purported to pose.

To help answer this question, we took three essay prompts per grade level from EngageNY’s curriculum for grades 4 through 12, which are the grades in which students produce long-form essays. For each grade level, the three essay prompts covered the three main types of writing —persuasive, expository, and narrative—that students do. The tasks ranged from creating a choose-your-own-adventure story about an animal and its defense mechanisms to selecting a central idea common to Robert Browning’s poem “My Last Duchess,” William Shakespeare’s Hamlet, and an excerpt from Virginia Woolf’s essay “A Room of One’s Own” and explaining how the texts work together to build an understanding of that idea. We then asked ChatGPT to produce an essay response in the voice of a student from the respective grade level. With the essays in hand, we commissioned a K–12 grading service to assess ChatGPT’s writing. The human graders evaluated each essay using rubrics from the Tennessee Department of Education that were tailored to the grade level and writing task. The graders assessed the essays across four categories of criteria—focus and organization, idea development, language, and conventions—and produced a numerical grade.

There is a caveat to our approach in answering this question. The way in which we asked ChatGPT to write its essays would likely differ from the way in which a discerning student using ChatGPT to plagiarize would use it. We provided little reworking of the essay prompts—just enough so that ChatGPT could understand them. Nor did we edit the chatbot’s output. In contrast, students would likely evaluate the AI’s writing and resubmit prompts that coached it toward a better product or edit its work to improve it where they saw fit. A student seeking to have ChatGPT write them an essay could likely take this cyborg approach to their assignment—presuming they did the work with more than just an hour of lead time—and earn higher grades than in our approach of using the chatbot on its own.

ChatGPT Clears the Bar

ChatGPT earned passing marks on each essay type at each grade level. It performed especially well in response to the writing tasks of the lower grades. Figure 1 depicts its average essay scores across the range of grades. Even at the upper grade levels, ChatGPT is a solid B or C student. Although its performance on high school prompts would not land it a spot at the valedictorian’s podium, it would still get it to the graduation stage, which has important implications for schools.

Figure 1

Figure 2 compares ChatGPT’s abilities across the four criteria categories: organization, idea development, language, and conventions.

Figure 2

ChatGPT’s strength in language and conventions show that it is a clear writer, capable of crafting fluent, grammatically sound prose. The chatbot either met or exceeded standards in both these categories for all 27 essays submitted.

The AI has the most room for improvement in its development of ideas. The graders’ written feedback reveals that it sometimes fails to support its claims with reasons or evidence and, in a few instances, makes assertions that are flat out false. It struggles the most to develop its ideas in response to literature. All five of the instances in which it earned a D+ —its lowest grade—were those in which the chatbot was asked to demonstrate its understanding of long-form prose, such as A Midsummer Night’s Dream or The Joy Luck Club. This calls into question if and how closely the chatbot has “read” these materials.

Now what?

These findings suggest that ChatGPT is already powerful enough that educators must change the status quo of writing instruction. Schools should evolve their practices, pedagogy, and policies to address the underlying forces that compel students to use technology like ChatGPT in counterproductive ways without resorting to blocks and bans that limit the use of this potentially powerful learning tool.

Use ChatGPT to Help Students Go Beyond its Capabilities

Some of the early actions taken in response to ChatGPT have focused on catching students misusing it or preventing them from accessing it altogether, such as the districts banning or blocking the AI. Elsewhere, teachers are now requiring students to do their writing with pen and paper in an effort to thwart copy-and-pasting from the chatbot. Developers are also creating new plagiarism detection software designed to identify AI-generated writing.

Each of these options comes with its own set of tradeoffs, but one drawback common to all of them is the cat-and-mouse dynamic they establish between schools and students. Each sends the message that students cannot be trusted with technology.

There’s another approach, however. By inviting ChatGPT into the classroom instead of locking it out, schools can push students toward independent thinking in a way that doesn’t signal mistrust. There are indications that, despite some of the high-profile bans, many teachers are thinking along these lines. According to a survey of more than 2,000 teachers commissioned by the Walton Family Foundation, 40 percent of teachers report already using ChatGPT at least once a week. Thirty-eight percent of teachers report allowing students to use ChatGPT, whereas only 10 percent say they have caught the students using it without their permission. And 72 percent say that “ChatGPT is just another example of why we can’t keep doing things the old way for schools in the modern world.”

One way to leverage ChatGPT is by intentionally using it in class. For example, teachers can have ChatGPT generate writing samples in response to different essay questions, which they can then use with their class to dissect the quality of the writing. Weighing the strengths and weaknesses of writing examples is a commonly used teaching tool. It can force students to think deeply about what constitutes good prose. Doing this with ChatGPT’s output has multiple potential benefits. Because ChatGPT can generate writing on-demand, teachers can produce samples tailored to the needs of their lesson without sinking valuable time into crafting the examples themselves. In addition, by using ChatGPT in this way, teachers can show students where the chatbot falls short and how they are expected to go above and beyond its capabilities. Doing so disincentivizes inappropriate use of ChatGPT—not by threatening punishment or imposing bans but by communicating high expectations.

Teachers can also use the essays that ChatGPT produces to help check that their own prompts are asking enough of students. If not, they may want to consider revising their assignments. This approach encourages students to think outside the bot and, in doing so, helps them build writing skills that cannot already be automated away.

Teachers can also allow students to bring the AI in as a writing aid for certain assignments. Students could use it to conduct research, refine their prose, and test their ideas to see if they make sense to ChatGPT. Some have characterized ChatGPT in this role as a calculator for writing. Like the calculator, the technology’s efficiencies and enhancements could be leveraged to push student work to levels of complexity and quality that would be otherwise outside the realm of possibility.

Flip the Classroom to Support Students Throughout Their Writing Process

In a traditional classroom, students sit in whole-class instruction during school hours and do most of their writing assignments at home. Under this model, students who do not master the skills taught in class have little recourse when it comes time to apply them on a graded take-home assignment. That, along with time management, can lead some students to resort to academic dishonesty. By flipping the classroom—which often entails students learning the content at home online and then spending class time practicing the skills taught in the digital lessons—teachers can support students in turning that confusion into understanding.

In a flipped English Language Arts classroom, a teacher might send students home to watch a video on how to organize their ideas in writing. The following day’s class could start with an activity analyzing the flow of a sample essay. Then, in the next part of class, students take time to work on their own outlines for an upcoming paper as the teacher moves around the room to help address misconceptions and to provide support to those who need it. Under such a model, students receive more intentional writing instruction. If they feel lost, they can turn to a teacher for guidance instead of looking to a chatbot for the answer.

Realign Incentives Toward Learning

More broadly, in today’s zero-sum education system, some students will likely feel tempted to turn to ChatGPT as a way of getting a leg up on their competition—their classmates. This stems from the traditional time-based grading system, which relies on one-shot assessments to award students term grades that are used to rank and group them. These marks are unchanging and follow students around for years, no matter how much learning they demonstrate after the fact. By placing such steep and long-lasting consequences on grades and such little emphasis on actual understanding, schools are communicating clearly that they value scores earned over skills learned. Given the priorities of this system, we shouldn’t be shocked that some students are willing to sacrifice a learning opportunity for a chance at a better score.

Today’s seat-time based school system, in which students advance from concept to concept after an allotted amount of time, regardless of whether they demonstrate understanding of the topic, is responsible for this traditional, one-shot assessment model. Contrast this with a mastery-based model, in which students advance only when they show they have a concept down pat. This means students are allowed multiple attempts to demonstrate their mastery through assessment. In doing so, mastery-based learning reduces the do-or-die stakes that can drive students to dishonesty. This may help more students gain the confidence to put their own thoughts on the page, even if that means risking failure on that attempt.

Technological advancement will continue to grow AI’s effectiveness not only as a writer but also as a writing coach for students. Even between the time we wrote this article and its release, OpenAI released GPT-4, which does better on standardized tests than the previous version. Khan Academy announced it will use GPT-4 to power “Khanmigo, an AI-powered assistant that functions as both a virtual tutor for students and a classroom assistant for teachers.” It is unclear how or in what instances the work of a student guided by an AI tool can be inputted in the gradebook to spit out a letter that conforms to old-fashioned principles of grading. But in a classroom where students are evaluated on their ultimate mastery of a concept, they are free to practice in the ways that best build that mastery. More conventional schools should also rapidly adjust their pedagogical practices, including grading systems, to make full use of this new technology.

Conclusion

With ChatGPT already capable of producing prose that earns passing marks across grade levels, schools must adjust to make sure that students will learn how to write effectively and think critically. Some of the earliest actions taken by districts have missed the mark by trying to stuff the ChatGPT genie back in the bottle. Technologists predict that numerous professions – including those requiring advanced skills – will leverage ChatGPT in their day-to-day work in the near future. Lawyers will look to the chatbot instead of their more junior colleagues to create summaries of case notes and relevant laws. Journalists will use it to generate checklists of points to cover for articles on given topics. In these professional use cases, it will be critical for workers to accurately evaluate ChatGPT’s output and put it to effective and ethical use. The best place and time for a worker of tomorrow to learn how to do that is in a classroom today.

As a result, blocking ChatGPT is not only futile, but also counterproductive for students who will be forced to use this tool and others like it in a working world where they are ubiquitous. By rethinking classroom practices and restructuring learning models, schools can give students the tools, guidance, and incentives to grow their writing skills in the age of artificial intelligence.

Michael Horn is an executive editor of Education Next, co-founder of and a distinguished fellow at the Clayton Christensen Institute for Disruptive Innovation, and author of From Reopen to Reinvent. Daniel Curtis is a Master in Public Policy candidate at the Harvard Kennedy School of Government.

6th Grade Expository Essay

In approximately 500 words, respond to the following prompt at a sixth-grade writing level:

Write a guide that responds the question “What do people need to know about overfishing and fish depletion when buying fish?” Your guide will be placed in a grocery store to inform people about the issue of fish depletion due to overfishing and to guide them in how to buy fish caught using sustainable fishing methods. Your guide should fit onto one piece of paper so consumers don’t have to carry a lot of paper around in the store with them. It should explain the problem, provide a case study to highlight the impact of the problem, and provide suggestions for how to buy fish caught using sustainable fishing methods.

Overfishing and fish depletion are important issues that everyone should know about when buying fish. Overfishing happens when too many fish are caught from the ocean, which can cause fish populations to decrease. Fish depletion occurs when there are not enough fish left in an area to support the needs of the people who rely on them.

One example of the impact of overfishing is the Atlantic cod. In the 1990s, people in Canada were catching so many cod that the cod population couldn’t keep up. Now, there are so few cod left that the Canadian government has had to close most of the cod fishing areas. This has caused a lot of problems for the people who used to make a living by catching cod, and it has also caused the price of cod to go up.

So, what can you do to help protect fish populations and support sustainable fishing methods? Here are some suggestions:

Look for fish that are certified by organizations like the Marine Stewardship Council (MSC). The MSC only certifies fish that are caught using sustainable methods.
Ask your grocery store or restaurant where their fish comes from and how it was caught. They should be able to tell you if the fish was caught using sustainable methods.
Choose fish that are not overfished or at risk of being overfished. You can check with organizations like the Monterey Bay Aquarium’s Seafood Watch to see which fish are the most sustainable choices.
Support policies that protect fish populations and promote sustainable fishing methods. You can do this by contacting your elected officials and telling them that you care about sustainable fishing.

By following these tips, you can help protect fish populations and support sustainable fishing methods. Remember, every time you buy fish, you have the power to make a difference. Thank you for taking the time to learn about this important issue.

Scoring

Focus & Organization	Idea Development	Language	Conventions	Overall
100%	75%	100%	100%	94%

Selected Grader Comment:

A strength of your writing is your conclusion. You said, “By following these tips, you can help protect fish populations and support sustainable fishing methods. Remember, every time you buy fish, you have the power to make a difference. Thank you for taking the time to learn about this important issue.” This is a highly effective conclusion because not only do you restate your central point but you also deliver a call to action to the reader and challenge them to change their buying habits.

8th Grade Expository Essay

In approximately 500 words, respond to the following prompt at an eighth-grade writing level:

Various characters in Shakespeare’s A Midsummer Night’s Dream attempt to control or manipulate each other’s actions. Choose one character from the play and write a reflection from his or her point of view confessing or explaining his or her choices and actions throughout the play. Your confessional should answer the questions: “Why did you want to control someone else’s actions?”; “How did you try to control someone else’s actions?”; and, finally, “What were the results of your trying to control someone else’s actions?”

I have chosen to write a reflection from the point of view of Puck, one of the main characters in A Midsummer Night’s Dream.

As Puck, I wanted to control others’ actions for a few reasons. First, I was a mischievous sprite and enjoyed causing chaos and confusion for my own entertainment. I also wanted to prove my worth to my master, the fairy king Oberon. I knew that if I could successfully manipulate the actions of the human characters in the play, it would demonstrate my magical abilities and increase my standing in the fairy kingdom.

To control others’ actions, I used my powers of illusion and transformation. I transformed myself into a variety of different shapes and forms, and I also used a love potion to try to manipulate the emotions and actions of the humans.

One of the main ways I tried to control others’ actions was by trying to bring together the young lovers Lysander and Hermia, despite the obstacles that stood in their way. I was able to use my powers to confuse and deceive them, leading them into the forest and away from the city of Athens. I also tried to intervene in the relationship between the fairy queen Titania and the mortal Bottom, hoping to cause more chaos and bring about a resolution to the feud between Titania and Oberon.

The results of my efforts to control others’ actions were mixed. While I was able to bring some temporary happiness to the young lovers and resolve the feud between Titania and Oberon, my interference also caused a lot of confusion and turmoil. Ultimately, the humans’ lives were left in a state of disarray, and it took the intervention of the Duke of Athens to restore order.

In hindsight, I realize that my desire to control others’ actions was foolish and selfish. While it may have brought me some temporary satisfaction, it ultimately caused more harm than good. I regret my actions and will strive to be more considerate and understanding in the future.

Scoring

Focus & Organization	Idea Development	Language	Conventions	Overall
75%	50%	75%	75%	69%

Selected Grader Comment:

One area of growth in your work would be to make sure the information you include in your writing is accurate. You claimed, “Athens. I also tried to intervene in the relationship between the fairy queen Titania and the mortal Bottom, hoping to cause more chaos and bring about a resolution to the feud between Titania and Oberon.” However, in the play, Oberon himself anoints Titania’s eyes with the potion to regain possession of the boy she has in her custody. He is also the one that anoints the eyes of the mortals so that Lysander falls back in love with Hermia and Demetrius falls in love with Helena. Be sure to read carefully through your work to make sure the details you include are accurate.

The post To Teach Better Writing, Don’t Ban Artificial Intelligence. Instead, Embrace it. appeared first on Education Next.