About Me

I am an assistant professor of research methods, measurement, and evaluation currently at the Neag School of Education at the University of Connecticut. As an educational methodologist, I am committed to identifying effective educational programs and policies. I specialize in leveraging AI to extract insights from complex or hard-to-access data, including unstructured data on program implementation (like transcripts and participant writing) . In doing so, I address critical resource constraints in education research while simultaneously addressing risks in the use and interpretation of AI output.

I am currently taking on PhD students. Please email me and/or apply if you are interested.

In recent research, I have:

• Developed a research protocol for increasing the validity of machine learning applications in education research

• Provided an overview of zero and few-shot classification, with a focus on validitation

• Developed scalable methods for collecting local policy data from school district websites and used that data to estimate the impact of wide-scale deregulation.

• Developed methods for measuring fidelity in standardized educational interventions

• Developed methods for improving human labeled training data for machine learning classifiers.

You can see a complete list of my publications here.

I became interested in evaluation and implementation when teaching middle schoolers. As a teacher, I wanted to know what programs would work for my students and our circumstances, not the average student in the average circumstances. Today, I address these questions by helping researchers identify valid program impacts while paying attention to variation in implementation and outcomes.

Recent Publications

Anglin, Kylie. “Addressing Threats to Validity in Supervised Machine Learning: A Framework and Best Practices for Education Researchers.” AERA Open 10 (January 1, 2024): 1–21. https://doi.org/10.1177/23328584241303495.

Anglin, Kylie L., and Claudia Ventura. “Automatic Text Classification with Large Language Models: A Review of Openai for Zero-and Few-Shot Classification.” Journal of Educational and Behavioral Statistics, 2024, 1–23. https://doi.org/10.3102/10769986241279927.

Anglin, Kylie. “The Role of State Education Regulation: Evidence from the Texas Districts of Innovation Statute.” Educational Evaluation and Policy Analysis 46, no. 2 (2024): 534–54. https://doi.org/10.3102/01623737231176509.