Universal Pre-K | National Institute for Early Education Research

Inquiring minds often want to know which states offer “universal pre-K.” As states vary in what they define as universal pre-K (UPK) and in how far they have progressed toward fully implementing a universal program as intended, the answer is somewhat complicated.

classroom learning

Regarding definitions, the term UPK can mean simply that the sole eligibility criterion is age, in contrast to “targeted” programs in which eligibility is limited by child or family characteristics, most commonly income. This does not mean that the program is available to all applicants, as there may be caps on spending or enrollment that limit the number of children who can be served. The other common definition–and what universally means in most other developed countries–is that every child can (and very nearly all do) enroll, just as children in the US do in first grade.

A further complication is that when states launch UPK, they often cannot simply enroll all children who might want to attend immediately. It takes some time to create capacity, and states vary in how quickly they increase enrollment. Perhaps more importantly, states that express the intent to enroll all children all too often lose the political will to do so before they reach that goal, and fail to increase funding to keep enrollment expanding until it serves all who wish to enroll. An added wrinkle is that states often provide funding that incentivizes school districts to offer UPK (directly or through private providers), but they do not require school districts to do so (although districts must accept all who wish to enroll if they do offer UPK). In such a situation, not every location in the state may make pre-K available.

State examples help clarify the variations in definitions and intent to implement. At present, only in Vermont; Washington, DC; and Florida can be considered fully universal, in the sense that every child can enroll and virtually all do, although in Florida, Head Start offers such a superior service that many families choose that over the state’s pre-K program. Oklahoma offers UPK in all but a few districts. West Virginia has been in the process of expansion, but may have reached ‘universal’ in 2015. Enrollment in these states varies from 99 percent, to as low as 70 percent in West Virginia which is still expanding (Barnett, Carolan, Squires, Clarke Brown, & Horowitz, 2015).

Five states–Georgia, Illinois (Preschool for All), Iowa, New York, and Wisconsin have policies that they and others call UPK for 4-year-olds, but which falls short of allowing all children to be served. Wisconsin is the only state with a specific constitutional provision for 4K, and will fund school districts to serve all children but does not require all districts to participate. Although the policy is quite similar to that in Oklahoma, fewer districts participate and enrollment remains substantially lower at 66 percent. In Georgia, enrollment is limited by the amount of funding available year to year, and enrollment has plateaued at about 60 percent. Iowa similarly serves about 60 percent at age 4, but it is less clear why it does not continue to expand. In New York, limited funding restricted enrollment and continued to do so, although New York City’s push to enroll all children led to implementing long-delayed increases in state funding to allow for expansion. Enrollment in New York is expected to reach 50% percent in 2015. Illinois is the most egregious example of the gap between intent or ambition and implementation. Designed to serve all 3- and 4-year-olds, the program has never enrolled even a third of age-eligible children. Illinois prioritizes low-income families for services, and currently serves only 27 percent at age four and 19 percent at age three (Barnett et al., 2014)

Finally, two states have unique policies that could be considered UPK of a sort. In California, Transitional K (TK) serves children who turn five between September 2 and December 2 of the school year. As these children then attend kindergarten the following year, kindergarten is effectively pre-K. Kindergarten is available to all children who meet the age cutoff. In New Jersey, a state Supreme Court order mandated universal pre-K in 31 high poverty districts serving about one-quarter of the state’s children. Within these districts the only eligibility criteria are residency and age–enrollment varies by district but ranges from 80 percent to 100 percent.

Considerations regarding access, enrollment, and quality

When evaluating policies, it is also important to understand that UPK programs vary in quality as well as actual enrollment. Schedules, standards, funding, and teaching practices vary widely across the “universal” programs described above. Some require as little as 10 hours per week. Others offer a full school day with before- and after-school care, potentially reaching 10 hours per day. Some leave virtually all policy choices and guidance up to the local school district or program. Florida requires little more than a high school diploma of teachers in school-year programs. Others, like New Jersey, set high standards that every classroom must meet, and provide extensive support and guidance. State funding ranges from $2,200 per child to $15,000 per child. Observations of teaching practices in statewide evaluations indicate that some programs are overwhelmingly good to excellent, while others are mostly poor to mediocre. States differ in their choices regarding how much to invest in quality versus quantity, although it is clear that there need not be a trade-off if states can muster sufficient political will (Minervino, 2014). Indeed, some have claimed that programs that do not reach most of the population may have difficulty obtaining support for adequate quality (Barnett, 2011).

–Steve Barnett and Rebecca Gomez, NIEER

What Is Personalized Learning?

Is it going to transform public schools, finally bringing education into the age of digitally driven personalization embodied by companies such as Amazon and Netflix? Or is it a billionaire-backed boondoggle, aimed primarily at replacing teachers and extracting data from children? When it comes to “personalized learning,” there’s no shortage of hyperbole from either proponents or critics.

Here’s what you need to know about the realities of one of the biggest, most controversial trends in K-12 education—starting with the most difficult question first.

What exactly is personalized learning?

Inside K-12 schools, the term is used to mean just about anything.

For many educators, it’s about using adaptive software that adjusts to each student’s skill level. Sometimes, it’s about the systematic use of digital data to inform big decisions, like how to group students. Other schools focus on giving students more say over what projects they undertake, or how they present their work. And increasingly, personalized-learning proponents also take a much wider lens, saying schools must nurture each individual child’s social, emotional, and physical development.

Some see such scattered and nebulous definitions as reason to worry that personalized learning will go the way of other short-lived reforms. Others are more positive.

“In the same way that Inuits have lots of different words for ‘snow,’ I think these are all personalized learning,” says Larry Bergerthe CEO of ed-tech company Amplify and a leading thinker and writer on the topic for over a decade.

What’s the hope behind the movement?

Very broadly speaking, the idea is to customize the learning experience for each student according to his or her unique skills, abilities, preferences, background, and experiences.

The hope is that it will improve a wide range of student outcomes, from engagement to achievement to wellbeing.

Personalized-learning pioneer Dianne Tavenner told Education Week in 2017 that it’s about the type of education good teachers have always envisioned, but haven’t always had the tools to make a reality.

“Personalized learning is a way to actually enact the pedagogy we believe in and that kids thrive in,” said Tavenner, the founder of Summit Public Schools, a California-based charter network that operates about a dozen of its own personalized-learning schools while licensing its personalized-learning software to hundreds of others.

So is this a new idea or not?

Not really.

The personalized learning movement has two primary wings, each of which is grounded in decades-old (and often warring) philosophies about how children learn. The so-called “engineering model” of personalized learning emphasizes efficient mastery of academic content. The idea is that experts can map out what each child needs to learn, measure what each child already knows, and then create the optimal path for him or her to learn the rest.

Other approaches to personalized learning are rooted in progressive education traditions. This wing of the movement generally holds that learning happens when schools tap into students’ interests and passions, giving them individualized opportunities to ask questions and explore and take risks.

The former approach dates at least back to the 1950s, when psychologist BF Skinner was experimenting with “teaching machines” intended to let students answer questions and receive feedback at their own pace. The latter goes back more than a century, to John Dewey. It’s often seen today in schools that emphasize more project-based learning.

In both cases, what is new is the way in which technology—from big data to online collaboration tools to social media—is being used to amplify methods educators have been using more or less forever.

Where did the new push for personalized learning come from?

Big-picture, it’s a reflection of deeper trends in both society and the K-12 sector.

Technology has already transformed other sectors of society, such as retail. Often, this has taken the form of using digital data to learn more about individuals and their preferences, then target them with information, advertisements, and recommendations. In part, personalized learning is a reflection of the push to apply those tools and ideas to education.

It’s also emerged out of rising opposition to standardized tests and the so-called “factory model of education,” which critics contend has left both children and teachers feeling like widgets inside the classroom. These broad forces started to come together in tangible form roughly a decade ago.

Beginning around 2009, for example, the Bill & Melinda Gates Foundation began investing hundreds of millions of dollars to support research and development around personalized learning.

Then, under President Obama, the US Education Department gave half a billion dollars to encourage districts to embrace the trend, primarily via its competitive-grant program known as Race to the Top. More recently, the Chan Zuckerberg Initiative, the venture-philanthropy group started by Facebook founder Mark Zuckerberg and his wife, pediatrician Priscilla Chan, has vowed to give hundreds of millions of dollars per year in support of its vision for “whole-child personalized learning ,” encompassing students’ emotional and physical development as well as their academic learning.

States, companies, other philanthropies, and a network of nonprofits and advocacy groups are also now backing the movement.

Do personalized learning strategies work?

Oh yeah. Big time.

In 2018, for example, the Education Week Research Center conducted a nationally representative survey of the country’s school principals.

More than half characterized personalized learning as either a “transformational way to improve public education” or a “promising idea.”

A whopping 97 percent said their schools were using digital technologies to personalize learning in some form or fashion.

Does personalized learning work?

That’s precisely the wrong question to ask.

John Panea senior scientist at the RAND Corporation and a leading researcher of the personalized learning movement says the reason why goes back to the incredible variations in how personalized learning actually happens in real classrooms.

“At this stage, we really need to be looking at the actual components of what people are trying to do and assess them each on their own,” Pane said.

That’s an argument that proponents generally embrace. They point to the strong research base for some of the core building blocks of most personalized-learning models, including providing students with differentiated instruction and real-time feedback.

Some studies of specific personalized-learning products, used in particular situations and under particular circumstances, have also yielded promising signs.

But other such studies have shown small or even negative results.

And what about personalized-learning models that seek to transform entire schools? Experts estimate there are maybe 1,000 or so schools in the country. How are they doing?

Summit is one of the best-known, best-funded examples, having received more than $40 million from the Chan Zuckerberg Initiative. But Tavenner’s group has declined to undergo independent third-party evaluation.

The results for other models that have been studied are generally not great.

“The evidence base is very weak at this point,” said Pane, who led a Gates-funded study of about 40 personalized-learning schools, finding modest gains and big implementation challenges.

Are there other arguments against personalized learning?

You betcha.

Critics such as independent researchers Audrey Watters warn that personalized learning is a pretext for “massive data collection” and surveillance of students. They point to the rapid adoption of analogous technologies in other sectors (think, for example, Facebook), before the unintended and adverse privacy-related consequences we are now seeing could be ironed out.

That 2018 Education Week Research Center survey also found that a strong majority of the nation’s principals worried that the trend was leading to too much screen time for students (85 percent expressed “some,” “a lot” or “a great deal” of concern), students working alone too often (77 percent), and the tech industry gaining too much influence over public education (67 percent.)

Where does all that leave schools?

Pane and his team at RAND say K-12 educators, administrators, and policymakers are in the unenviable position of having to make high-stakes educational decisions with “imperfect evidence.”

That doesn’t mean they should stick their heads in the sand, the RAND team said. Personalized learning holds promise. Careful, cautiously attempts at some elements of the trend may make sense. Stick to common sense and the evidence we do have, they advise. Resist the pressure to throw out established practices that work just because they’re not new and shiny.

But think twice before diving in.

“I would not advise schools to dump massive resources into going completely into personalized learning,” Laura S. Hamilton, a senior behavioral scientist and distinguished chair in learning and assessment at the RAND Corporation, told Education Week in 2017. “Experiment with some new approaches that might be a good fit for your particular school or district, but monitor it very closely.”

How Do We Define and Measure “Deeper Learning”?

“Students can’t learn in an absence of feedback,” Pellegrino said. “It’s not just assessing, but providing feedback that’s actionable on the part of students.”


In order for deeper learning to become the norm rather than the exception, it has to be a priority for local, state, and national policymakers, said Linda Darling-Hammond, professor of education at the Stanford and advocate for education reform. Common Core State Standards, which began to push towards critical reasoning and problem solving and application of knowledge, are only being applied to math and literacy, she said. “What about other subjects?”

What’s more, social-emotional skills have to be taken into account anytime we address deeper learning, she said. Some states have developed standards for social emotional skills, and it could be a good strategy for others to follow as well.

The way to achieve deeper learning is through curriculum and instruction, in assessments, and teachers’ professional development, she said.

The curriculum schools use now was created by a 10-member committee of men in 1893, Darling-Hammond said.”We need a new committee,” she said. “Maybe with women and with people of color, and maybe even with 20 people.”

Curriculum should go deeper into application of skills, cover fewer topics that are more carefully selected and more deeply taught, and she said Common Core tries to do this. She repeated the mantra of many progressive educators: “Teach less, learn more.”

As for assessment, Darling-Hammond said our goals must be far more ambitious than they are now. Policymakers should follow the lead of schools that have used digital portfolios and projects as assessments, rather than relying on standardized tests. “Students are able to take feedback and revise their work,” she said. “Their conscientiousness is tested. We know that in contexts like that, we have evidence that students are making it through college in higher numbers.”

Our current standardized tests focus on recall of facts and procedures, the lowest levels of types of learning, Pellegrino added. “They’re easily scored and quantified for accountability procedures. They’re not optimal in measuring the kinds of competencies that represent deeper learning,” he said.

But in order to use assessments that are valuable to students, we need to invest more money and time. “The kinds of tasks we need to assess take kids more time to act and more time to score,” she said. Currently, the US spends $10 to $20 per child on assessments, but in other countries where children are doing deep inquiries and investigations, assessments cost about $200 per student.

“We need to rethink the way we make those investments, as part of our policy agenda,” she said, because, as Pellegrino put it, what gets tested governs what gets taught.

Another big component of deeper learning involves collaboration, she said, and “collaboration is not cheating… it’s part of problem-solving. Collaboration is a skill not a deficit.”

Professional development is another key part of bringing deeper learning to students. School principals, who play a big role in curriculum adoption, as well as educators, must learn about problem-solving, child development, and content pedagogy in order to understand how to set up collaborative and project-based learning.

But in order to do their jobs well, educators must be given enough time to create a thoughtful curriculum. In other countries, Darling-Hammond said, educators are allocated 15 to 20 hours a week just dedicated to curriculum creation.

For those interested in pursuing deeper learning strategies in class, she suggested pulling out the key ideas from current standards and going deep into those subjects, such as ratio and proportion in math. She also suggested reading books and learning more about complex instruction and how to develop collaborative group work, even in classes where there’s a wide range of student skills.


From an Edweek article that reported on findings from the same study:

The committee pointed to a 2008 five-year longitudinal study of 700 California students in three high schools: one urban and one rural school, each with large proportions of minority and English-language learner students, and another overwhelmingly wealthy, white school. While at the start of the study, incoming 9th graders in the diverse urban school performed significantly below the students in the other schools in mathematics, the school designed its algebra and geometry courses to highlight multiple dimensions of mathematics concepts and approaches to problem-solving, self- and group-assessment and developing good questions. When tested at the end of the first year, the students exposed to the “deeper learning” mathematics had caught up with their peers in algebra, and they performed significantly better than students in the other schools in the following year. By the 4th year of the study, 41 percent of students at the urban diverse school were taking calculus, in comparison to only 27 percent at the other two schools.

The study was partially funded by the William and Flora Hewlett Foundation.

GPT Chat: What is it?

Chat GPT is an artificial intelligence program that generates dialogue. Created by Open AI, this high-capable chatbot uses machine learning algorithms to process and analyze large amounts of data to generate responses to user inquiries. This language processing program is able to understand human language as it is spoken and written, allowing it to understand the information it is fed, and what to spit back out. A student can type in a question, and ChatGPT spits back out an easily understandable answer – in a variety of formats with precise stipulations.

For example, you can ask the question, “Explain how climate change affects endangered species.” You can tell it, “Write me a poem,” and when it does, say, “Now make it more exciting.” You even ask it to create a reference page and use APA 7th edition.

More about ChatGPT:

ChatGPT: Everything you need to know
What is ChatGPT and How is it Used in Education?

One of the key features of GPT chat is its ability to generate responses like humans in real-time, based on the user’s input. It can give natural answers to questions in a conversational tone and can generate stories, essays, and poetry. Moreover, GPT Chat can:

  • Answer questions
  • Solve math equations
  • Translate between languages
  • Debug and fix code
  • Write a story/poem
  • Classify things

Perhaps more amazing is the ease with which ChatGPT produces these responses. Students could potentially spend hours researching and drafting an essay on quantum mechanics, whereas ChatGPT can produce a well-written alternative in seconds.

While ChatGPT can populate a pristine essay on the cultural impact of the Spanish-American War, there are limitations. Due to its infancy, the chatbot may generate incorrect information or have a comprehensive understanding of a topic because answers are based on data that is limited to 2020 and prior.

Here’s what ChatGPT can do:

Five Amazing Things People Have Done with Chat GPT

Pulling from a large dataset of text, Chat GPT uses this dataset to learn about language, grammar, and the structure and meaning of words and sentences. This enables it to understand the context and intent of user queries and generate appropriate responses.

AI process models

© OpenAI

Source: OpenAI

While ChatGPT is a huge advancement in technology, it poses serious concerns and challenges for learning. This appears to be the newest wave of academic dishonesty, which is quickly turning into a tsunami. There are technologies such as GPTZero that can detect plagiarism, but the greater concern is that students are not engaged in the writing process and missing opportunities for research, critical thinking, and formulating their own response.

Understandably, many faculty are responding with panic and considering oral assignments or detection tools to combat plagiarism. Rather, faculty should be encouraged to harness the tool’s potential to aid instructions.

So, how can Chat GPT actually help faculty or students in the classroom? Let’s ask Chat GPT:

How can Chat GPT actually help faculty or students in the classroom?

Teachers can use ChatGPT, a large language model trained by OpenAI, in the classroom to engage and educate students in a variety of ways. Here are a few ideas:

  • As a writing prompt generator: ChatGPT can help teachers generate engaging writing prompts for students to respond to. For example, a teacher could ask ChatGPT to generate a story starter or a creative writing prompt, and then have students use the prompt as the basis for their own writing. This can be a fun and interactive way to get students excited about writing.

  • As a reading comprehension tool: ChatGPT can be used to help students improve their reading comprehension skills. Teachers can ask ChatGPT to generate a passage on a topic that students are studying, and then have students read the passage and answer questions about it. This can be a helpful way to assess students’ understanding of the material and to identify areas where they may need additional support.

  • As a vocabulary builder: ChatGPT can help students expand their vocabulary by generating sentences using words that students may not be familiar with. Teachers can ask ChatGPT to generate sentences using a particular word, and then have students guess the meaning of the word based on the context of the sentence. This can be a fun and interactive way to help students learn new words and improve their vocabulary.

Overall, ChatGPT can be a valuable tool for teachers looking to engage and educate their students in new and exciting ways. By using ChatGPT in the classroom, teachers can help students develop important skills such as writing, reading comprehension, and vocabulary building. (www.helloteacherlady.com)

The above text was written by Chat GPT in lesson that one minute. Imagine the amount of time that can save faculty, not to mention the possibilities for learning in the classroom.

More advice on using ChatGPT in the classroom

ChatGPT Advice Academics Can Use Now
Embrace the Bot: Designing Writing Assignments in the Face of AI
Unleash the Power of GPT Chat in Education!
Yes, you can use Chat GPT with Students:

Chat GPT Across the Curriculum

CETAL hosted a special workshop, led by Dr. Jen Talbot, to address the concerns and suggested responses to this new technology. She provided an overview of Chat GPT’s capabilities and a collection of suggested approaches, as well as an opportunity to collaboratively brainstorm likely effects in our respective disciplines and assignment-specific strategies to address those effects.

View the Chat GPT presentation recording
View the Chat GPT presentation slides
View the ChatGPT presentation handout


Bowman, Emma. (2022, December). ChatGPT could transform academia. But it’s not an A+ student yet. NPR. https://www.npr.org/2022/12/19/1143912956/chatgpt-ai-chatbot-homework-academia

D’Agostino, Susan. (2023, January 20). Academics work to detect ChatGPT and other AI writing. Inside Higher Ed. https://www.insidehighered.com/news/2023/01/20/academics-work-detect-chatgpt-and-other-ai-writing?utm_source=Inside+Higher+Ed&utm_campaign=6771fc5f7b-DNU_2021_COPY_02&utm_medium=email&utm_term=0_1fcbc04421- 6771fc5f7b-199977845&mc_cid=6771fc5f7b&mc_eid=007c4da0db

Kramer, Zoe. (2022, December). What is ChatGPT and how does it work? Freshened. https://www.freshered.com/what-is-chat-gpt-and-how-does-it-work/

Hughes, Alex. (2023, January 16). ChatGPT: Everything you need to know about OpenAI’s GPT-3 tool. BBC Science Focus Magazine. https://www.sciencefocus.com/future-technology/gpt-3/

Mintz, Steven. (2023, January 16). ChatGPT: Threat or menace? Higher Ed Gamma. https://www.insidehighered.com/blogs/higher-ed-gamma/chatgpt-threat-or-menace

Ramin, Shana. (2022, December 13). 3 ways teachers can use ChatGPT in the Classroom, According to ChatGPT. Hello, Teacher Lady. https://www.helloteacherlady.com/blog/2022/12/3-ways-teachers-can-use-chatgpt-in-the-classroom-according-to-chatgpt

Nicola Sturgeon’s ambition on education defines her leadership

Nicola Sturgeon set out her stall right from the start of her tenure as Scotland’s first minister or, if you’re being less generous, she built a rod for her own back.

Education was to be her number-one priority. It never felt like it had been for her predecessor, Alex Salmond, but when Sturgeon took power unchallenged late in 2014, surf and fuelling the surging popularity of the SNP after the independence referendum, she was bold in her ambition for education.

In a defining speech of her early days as FM, in August 2015, Sturgeon said she would put her “neck on the line” by asking that her record ultimately be judged on whether Scotland eliminated the disadvantage-related attainment gap that had blighted education since anyone could remember.

In the months and years that followed, there was some semantic jiggery-pokery: the message seemed to morph so that the government was seeking to “close” the attainment gap as in narrowing it, rather than eliminating it altogether.

Regardless, that speech, delivered at Wester Hailes Education Center in Edinburgh, became a weapon that opponents regularly used to attack the FM and her government. Scottish education was failing, they said, and was an indelible stain on the record of the leader who had made it his priority.

Of course, the truth about Scottish education during Sturgeon’s time as leader was more nuanced than it is often portrayed and where there was progress, much of it was reversed by the Covid pandemic. But she had left herself wide open to such attacks.

With hindsight, Sturgeon’s decision in 2015 to set out such an audacious some might say unachievable ambition to eliminate the attainment gap has to be understood in the context of the time. Her popularity ratings were through the roof even now they remain relatively high – and the No vote in the referendum, far from cowing the SNP, had persuaded tens of thousands of people to join its ranks in the aftermath of the September 2014 plebiscite.

Anything seemed possible, so what now appears hubristic must have looked to Sturgeon’s supporters like the sort of self-fulfilling prophesy that popular new leaders like to shoot for when playing the long game of legacy. “We choose to go to the Moon,” said JFK; Nicola Sturgeon was now choosing to eliminate the attainment gap, unperturbed that many previous generations of political leaders of all stripes had singularly failed to do so.

Sturgeon puts the spotlight on education

What Sturgeon certainly achieved was to put education front and center in the Scottish Parliament. And, for better or worse, her focus on education paved the way for the Scottish Attainment Challenge, the Pupil Equity Fund, the near-doubling of free early years hours, the Scottish National Standardized Assessments and much else besides that is part of the furniture of Scottish education in 2023.

Are we now heading towards an era where education is on the sidelines again? Maybe things are already going that way. Certainly, the Scottish government has never given the impression over the past year that a quick end to the teachers’ pay dispute is a priority. On the other hand, if Sturgeon’s departure means education is less of a political football, many will see upsides to that.

Today, as Sturgeon reflected on her record after eight years as first minister, mentions of education were conspicuous by their absence. She ticked off achievements in making university more accessible to students from poorer areas and in offering 1,140 free early years and childcare hours, and underlined that her commitment to care-experienced young people will endure beyond her time as first minister.

But that was it. Judge me on my education record, Sturgeon said in 2015. Today, she barely talks about it.

Henry Hepburn is Scotland editor at Test. He tweets @Henry_Hepburn