Why is it so challenging to conduct research in K-12 education?

Why is it so challenging to conduct research in K-12 education?

The Intricacies of Conducting Research in K-12 Education: An In-Depth Analysis

Our country desperately needs an overhaul in K-12 education. In order to make this a reality, the quality of supporting research is essential. Research in K-12 education is often hampered by a number of challenges, making it difficult to conduct rigorous studies. This blog explores the challenges our K-12 researchers face today as well as possible solutions. 

Ethical Considerations

Human subjects research is governed by ethical considerations, especially when involving children. Any legitimate research that includes humans must go through an Internal Review Board (IRB). This process can vary from institution to institution as well as the nature of the research being proposed. Generally the steps include determining if the IRB is necessary, developing a research plan, completing an application to the IRB, submitting the application, responding to follow up requests and questions form the board, IRB edits and/or potential research design improvements, then receiving approval or “sigh” more required  changes prior to approval. This is a lengthy process and further complexity is introduced by funding and the needed consent from participants.  

The well-being and privacy of students will always be prioritized by parents, educators, and researchers alike. Therefore, obtaining informed consent from parents or guardians can be arduous and time-consuming. Study designs must respect students’ rights and protect their welfare while also remaining scientifically valid. Balancing all of the components of privacy, consent, and meeting the expectations of your institution and/or funders is not for the faint of heart.

Diverse Settings

From public to private institutions and from rural to urban environments, K-12 education encompasses a wide range of school types. The diversity of these populations can make it difficult for researchers to generalize their findings to broader populations or to draw conclusions that can be applied to a variety of contexts. There may also be unique policies, procedures, and curricula within each school and district that may affect research results.  It is also important to consider the intent of any study performed within the K-12 setting. There is some precedent for data being misused in ways that offset equity in the US.

“If we are imposing measures of success on communities, we are essentially also then imposing our values and agenda on them. Communities have been burned and harmed by the ways that measurement has been weaponized in past education reform efforts without their involvement.”

Confounding variables

It can be difficult to isolate the effects of a particular intervention or practice in educational research because of the complex interplay of factors that influence student learning. Among these factors are classroom dynamics, socioeconomic status, student motivation, parental engagement and teacher quality. Accounting for these different variables is often complex and time-consuming. The teacher shortage is also causing inconsistencies in resources that exacerbate the teacher quality and can strain new strategy implementation.

Resource constraints

K-12 education research often requires significant time, money, and human resources. In order to understand the long-term effects of educational interventions, longitudinal studies can span several years and require ongoing funding. Schools and teachers are often reluctant to participate in research projects having concerns about disrupting their daily routines and time away from instruction. Many teachers are also very much focused on raising state test scores and often fear variation from prepping towards their teaching goals. Lastly, even with district buy-in for a study, researchers also end up having to coordinate directly with individual schools for execution. 

Messy Data Issues

The arduous process of accessing K-12 education data can be extremely frustrating. This is especially true when the data is messy and almost impossible to aggregate for research purposes.  In spite of the fact that schools and districts have enormous amounts of valuable data, that data is often siloed, difficult to aggregate, or disorganized. Researchers are often unable to extract useful insights from school data due to its disorganization and disaggregation.

Additionally, because centralized school data is already difficult to parse, bringing in outside systems (such as disparate assessment providers) or giving them access to school insights from outside tutoring companies or professional development providers can also hinder or slow down progress.

Political and policy pressures

Changing policy priorities and a heated political climate also affect education, creating more challenges for researchers. It is possible for political agendas and policy changes to dictate which research areas receive support or funding, hindering the exploration of innovative ideas. Policy makers are focused on ROI in the final year of ESSER due to high expectations for reporting. State tests and NAEP scores in 2024 will remain the primary focus of governors’ offices. 

The level of focus on ROI may make it challenging to try new things or implement research that goes beyond basic third-party evaluations.  It is also possible for researchers to be pressured to produce results that support a particular policy or program. Their objectivity and integrity can be compromised by this kind of pressure. 


Educating children is a complex endeavor, involving ethical considerations, diverse learning environments, confounding variables, and  resource constraints. In order to overcome these challenges and contribute to the improvement of education, researchers, educators, policymakers, and other stakeholders must collaborate and be willing to adapt and innovate.

A number of solutions are possible, including simplifying the informed consent process, creating standardized research methodologies across multiple educational contexts, and advocating for increased funding and support for long-term, objective research.

Some additional solutions might include:

  1. Creating Collaborative Research Networks that establish long term research relationships with key K-12 stakeholders.  
  2. Interdisciplinary Approaches: Researchers can collaborate with experts from other fields to bring a multidisciplinary perspective to their research. This can help to address the complex and multifaceted nature of the challenges facing K-12 education, and can lead to more innovative and effective solutions.  This approach may also help with LEA and school level buy-in. 
  3. Technology-Based Solutions: It may be possible to set up more robust data aggregation that are inherently part of native school data systems.  This could streamline the research process and make it more efficient. For example, online survey tools, data management software, and educational data analytics platforms could help researchers identify possible research and better collect, manage, and analyze data already collected. 

Our goal at Pearl is to unlock educational research’s potential to improve K-12 education in the US. We are always looking for creative ideas and partners to help bridge the research to practice gap.  Please reach out anytime to schedule a discussion.

To Access Great Education Research with a focus on tutoring – NSSA Research Repository

Unsure of how to tackle the challenges of your large online tutoring program? Schedule time to speak to a Pearl expert and learn best practices for evidence-based tutoring with Pearl.

The Implications of Large Language Machine Learning Models in Tutoring

The Implications of Large Language Machine Learning Models in Tutoring

Since ChatGPT was released to the public via OpenAI the education community has been in constant chatter about its implications for learning. A large language model is a machine learning system that uses vast amounts of data to generate human-like language and perform natural language processing tasks such as text generation, translation, summarization, and sentiment analysis.

If you have not experienced ChatGPT you should. It’s definitely an exciting next generation in how we think about searching on the internet. For almost a quarter of a century Google has been the cornerstone of where we find information online. Google presents relevant links based on search. With ChatGPT information is presented in natural language and feels much more like a chat with someone very knowledgeable about the question you ask. 

Although the conversation feels fairly natural and the answers are cogent, they are not always correct. That being said, if you have a decent understanding of a subject you will probably find that the chat feels authentic and most of the time pretty accurate.  

When the AI was released everyone at Pearl was interested in jumping quickly and trying to understand the implications for tutoring. We spend a lot of time thinking about equity and imagine a world where anyone that needs a tutor could have a tutor. None of us is convinced that AI could replace a human, but I do think that AI has the capacity to make someone better at tutoring or give more opportunities for people to teach.

Here are some interesting implications for the tutoring industry:


Without compromising any person’s identity a tutor admin can give a list of characteristics of a learner and then ask to see corresponding characteristics of a tutor. Below is an example of a question and ChatGPT’s answer:


“Based on the research, what are 5 strong characteristics to look for in a tutor that would match well with a 9 year old Asian dyslexic child coming from a poor socioeconomic background learning in English whose first language was Chinese?”


“Great question! Here are five strong characteristics to look for in a tutor that could match with an Asian 9-year-old dyslexic child coming from a poor socioeconomic background learning in English whose first language was Chinese:

  1. Patience: A tutor who is patient can help the child feel comfortable and confident as they learn. Dyslexia can be frustrating and challenging for a child, especially when they are also trying to learn a new language. A patient tutor can help the child to feel supported and encouraged.
  1. Multisensory approach: Dyslexic children can benefit from a tutor who uses a multisensory approach to learning. This means that the tutor can use different senses, such as sight, sound, and touch, to help the child learn. For example, the tutor could use visual aids, like pictures or diagrams, or use physical activities to help the child understand the material.
  1. Experience working with dyslexic children: It’s important to find a tutor who has experience working with dyslexic children. This experience can help the tutor understand the unique challenges that dyslexic children face and how to tailor their teaching methods to meet the child’s needs.
  1. Cultural sensitivity: A tutor who is culturally sensitive can help the child feel understood and respected. It’s important to find a tutor who is familiar with the child’s cultural background and can be sensitive to their unique needs and experiences.
  1. Flexibility: Finally, it’s important to find a tutor who is flexible and can adapt to the child’s needs. Dyslexic children can learn at different paces and in different ways, so the tutor should be willing to adjust their teaching methods to meet the child’s individual needs. Additionally, the tutor should be flexible in terms of scheduling and availability to ensure that the child can receive consistent support.”


Once ChatGPT or some version of this type of AI is available, an admin could ask AI to construct a calendar based on the data for two tutors.  Here is an interesting example of ChatGPT’s response to a basic scheduling prompt.


I am a tutor that needs to meet with my student three times a week for 30 minutes each time.  I would like to know the dates I can meet with that student in school based on a typical school calendar.


The specific school calendar will depend on the school district and location. However, in general, most schools in the United States operate on a traditional academic calendar, with two semesters per year (fall and spring) and breaks for holidays and summer vacation.

To determine the possible meeting dates, you can start by looking up the school district’s academic calendar online or contacting the school directly to get a copy of the calendar.

Assuming a typical school calendar, here is a general example of possible meeting dates for a tutor meeting three times a week for 30 minutes each time:

  • Fall Semester: September to December (approximately 16 weeks)
    • Possible meeting dates:
      • Monday, Wednesday, Friday: September 6th to December 16th (excluding holidays)
      • Tuesday, Thursday, Friday: September 7th to December 16th (excluding holidays)
  • Spring Semester: January to May (approximately 16 weeks)
    • Possible meeting dates:
      • Monday, Wednesday, Friday: January 10th to May 20th (excluding holidays)
      • Tuesday, Thursday, Friday: January 11th to May 20th (excluding holidays)

Keep in mind that these dates are approximate and may vary depending on the specific school calendar. It’s important to confirm the exact school calendar with the school or district to ensure that the meeting dates are accurate.”


We’re starting to get into the interesting part now. Obviously, it is imperative that the teacher’s knowledge confirms, in some way, whether the ChatGPT response is helpful. As an example, ChatGPT can help tutors contextualize or better consider a student’s learning style or interests in order to support their tutoring. Let’s see if ChatGPT builds some math problems based on two factors (age and affinity) based on my son’s interest in trucks and construction equipment.


My son is 12 years old and has a strong affinity for trucks and construction equipment.  Based on his age and interests please produce 3 great ways to teach him long division. 


If your son has a strong interest in trucks and construction equipment, incorporating these interests into his long division lessons may help him stay engaged and motivated. Here are three great ways to teach him long division:

  1. Use visual aids: Use pictures or diagrams of trucks and construction equipment to explain the steps of long division. For example, you could use a picture of a dump truck to represent the dividend and use smaller pictures of construction equipment, such as bulldozers or excavators, to represent the divisor and quotient. This can help your son visualize the process and make it more concrete and meaningful.
  1. Turn division into a game: Create a game that uses trucks and construction equipment to teach long division. For example, you could create a game where your son has to use a dump truck to carry a certain number of building materials and use excavators to divide the materials into equal groups. Each time he successfully divides the materials, he can move to the next level of the game. This can make the learning process more fun and interactive.
  1. Use real-life examples: Find examples of how trucks and construction equipment are used in real-life scenarios that involve division. For example, you could use examples of construction projects where trucks have to haul and divide large quantities of materials. This can help your son see the practical applications of division and make it more relevant to his interests.

Remember, every child learns differently, so it’s important to find an approach that works best for your son. Incorporating his interests and making learning fun can go a long way in helping him stay motivated and engaged in the learning process.


Assessment is the final interesting implication for tutoring.  At Pearl, we believe the key to tutoring is quick formative assessments that verify student learning and identify areas where knowledge or understanding might be lacking. Once again, this is a great way to leverage several variables in a question. The following are two examples that you may find interesting:


Please give me three formative assessment questions that will help me validate that my 9 year old student understands long division.


  1. Can you explain the steps involved in long division and how they relate to each other?
  1. Can you solve a long division problem independently and explain how you arrived at your answer?
  1. Can you apply long division to solve real-world problems and explain how you arrived at your answer?


Please provide me with 3 problems to solve that would assess my 9 year old’s understanding of the basics of long division.


  1. 84 ÷ 6 = ?
  1. 145 ÷ 5 = ?
  1. 232 ÷ 8 = ?

Note: These problems are designed to test the student’s understanding of the basic steps of long division. When assessing your student’s responses, make sure to check that they have correctly used the divisor, dividend, quotient, and remainder, and that their final answer is correct. It’s important to provide feedback on their work and address any areas where they may need additional support or practice.


When tutoring programs consider using ChatGPT or any of the other emerging large language model AI tools, they must validate the tools carefully.  It is possible to speed up certain processes, but there is a cost associated with it.  There is a possibility that AI is extrapolating biases that are not aligned with your ethics.  Additionally, tutors should cultivate value that reflects their approach to tutoring and not rely too heavily on computers.  Relationships are at the heart of tutoring, so it’s important to foster connections and care throughout the process. Nevertheless, keeping up with the changing world is essential.  There is no doubt that our students will benefit from this new tech; therefore, as educators to the next generation, we need to keep our eyes on the ball. 

Now, for kicks, let’s let ChatGPT have the final word ?


What are the implications of Large Language Machine Learning Models in Tutoring


Large language machine learning models have several potential implications in tutoring, including:

  1. Personalized Learning: These models can help provide more personalized learning experiences for students by tailoring the content and pace of the instruction to their individual needs, interests, and learning styles.
  1. Immediate Feedback: The models can provide immediate feedback to students on their work and progress, helping them identify areas where they need additional practice or support. This can help students stay engaged and motivated and can also help teachers more effectively monitor student progress.
  1. Automated Scoring and Grading: These models can help automate the grading and scoring of student work, freeing up time for teachers to focus on providing individualized instruction and support to students.
  1. Improved Accessibility: These models can help make tutoring more accessible to a wider range of students, including those with disabilities or who speak different languages.
  1. Improved Instructional Design: These models can help identify patterns in student learning and suggest improvements to instructional design and content, helping teachers to more effectively support student learning and improve outcomes.

However, there are also some potential challenges and limitations to the use of large language machine learning models in tutoring, including issues of privacy and data security, the potential for bias in the algorithms used to analyze and evaluate student work, and the need for teachers to be trained in how to effectively use and interpret the results of these models.

The End…

Breaking Down the 3 Benefits of District Partnerships in Higher Education

Breaking Down the 3 Benefits of District Partnerships in Higher Education

Across the nation, Community Partnerships are forming, where HigherEd institutions partner with local K/12 school districts to provide evidence-based tutoring to younger students in their backyard. These partnerships offer states and districts an interesting alternative to traditional, for-profit tutoring partnerships. These community partnerships offer 3 unique advantages that could lead to a greater impact on student success than traditional tutoring programs and a more sustainable tutoring model. 

  1. If designed correctly, these partnerships can help improve the academic achievement of K/12 students. Providing access to high-impact tutoring, which meets the standards set forth by the National Student Support Accelerator, gives students the individualized support they need to succeed in school and mitigate learning loss. This can help close the achievement gap and ensure that all students have an equal opportunity to succeed.
  1. These partnerships can provide valuable professional development opportunities for university students interested in careers in education and create a pipeline of talent for local districts. By participating in tutoring programs, university students can gain hands-on experience working with K/12 students and can develop the skills and knowledge they need to become effective educators. They will also build relationships with local principals and superintendents, leading to career opportunities in the schools and inevitably addressing the teacher shortage. Deans For Impact is a non-profit that is focusing on these partnerships and has developed specific training content for future educators who are participating in community-tutoring partnerships. 
  1. Last but certainly not least, these local partnerships between universities and local school districts can foster a sense of pride and ownership within the community. By working together to support the academic success of K/12 students, universities and schools can demonstrate their commitment to the local community and can help build stronger, more supportive relationships with families and other community members. Because both the university and district are in the same town/region, these programs can provide more culturally relevant instruction and mentorship to their students. We see this in the state of Virginia, where Urban Leagues are partnering with HBCUs to provide academic mentorship to students in local districts. This approach can help create a sense of shared responsibility for student success.

Overall, these sustainable partnerships between universities and local school districts can provide a wide range of benefits for K/12 students, university students, and the community as a whole. By providing evidence-based tutoring and other support, such partnerships can help improve academic achievement, develop a talent pipeline for future teachers, and create a more collaborative, supportive learning environment for all students.

Planning for Online Instruction

Planning for Online Instruction

Planning for online instruction isn’t really different from planning for in-person instruction – you need to know who you’re teaching, what you’re teaching, and how you’re teaching your students. However, there are a few significant differences that can impact the successful delivery of your online lesson. In order to avoid the pitfalls of teaching online, you must plan out what you want to achieve with your students and how you’re going to make this happen. At the same time you need to plan for what could happen and how to respond to expected and unexpected issues. If something can go wrong with your technology or your students’ tech, it usually will. 

Let’s explore some important considerations of online instruction. Imagine you have a student who needs help with understanding measurement.

1. It’s always important to start by creating an objective for your lesson. What is it you want your students to learn?

2. Identify the means and the medium that you will use to teach your students. Will you be teaching using a hybrid model of online and in-person instruction (blended learning); live, online-only session (synchronous); posting lessons online for students to work through (asynchronous); or some combination of synchronous and asynchronous instruction? Will you be sharing a website or any links that students will need access to?

3. Review the limitations and affordances of the medium that you have selected. If you choose to use a mix of both synchronous and asynchronous instruction, you can create a library of videos for students to watch before, during, and/or after their live sessions with you. During live, synchronous lessons you can have students measure objects around the room with a ruler, you can have them use measuring cups to examine liquid measures, or use a scale to measure weight. You may find that there is an advantage to having students use the tools and objects in their own homes because it can create the relevancy that in-person instruction cannot.

4. Explore how you plan on interacting with your students, as well as if and how you would like them to interact with each other. Are you simply lecturing to your students, are you discussing topics as a class, or are you assigning students to groups?

5. Identify and share a plan for how you plan on communicating with students and their parents (phone calls, emails, texts, school portal, etc.), as well as the different channels you will use to distribute and collect their assignments. Will students be using a shared Google folder or will they be responsible for emailing or uploading their assignments?

6. Make plans to go over all of your expectations with your students and include different opportunities for you to model these behaviors for them.

7. Have a backup plan! Murphy’s Law says what can go wrong will go wrong, and this couldn’t be more true than with technology. Include hardcopies of your syllabus and assignments for students, so that they have more than one way to access essential information. Also, include and review instructions regarding what students should do when they are having tech issues, and/or they cannot access your online class. Don’t make students or their parents have to guess what they’re supposed to do – follow up with students right away when they miss class or assignments.

8. Put yourself in your students’ shoes. When you teach in-person you have a captive audience, students are stuck with you whether the lessons work for them or not, but when they are learning online and students are not engaged, they can very easily find something else to do… camera’s suddenly turn off and/or computers “suddenly” disconnect. Construct your lessons so that students have buy-in and are engaged in their learning.

9. Think outside the box. Students don’t need to sit in front of the computer the entire lesson, even when the camera is rolling – it’s okay for them to work quietly. You can also take students on an adventure … take them on an adventure as you measure things around your room. Teaching online gives you the opportunity to build a bridge between the people and things students interact with every day, and the lessons you are teaching them.

Planning for online learning is not more of a challenge than planning for in-person instruction, it is a different type of challenge. As an instructor, you just need to identify all of the parts of the lessons and how they will fit together. In addition, you need to consider some of the barriers that you’ll encounter, and be prepared to address them. Not every student will be thrilled about learning online, but most will adapt, and many will come around to seeing the perks if you are able to engage them in your online lessons.