Craft Data Science Insights: A 40-Minute Exploration – Session #3

Get ready to be inspired! This miniseries brings together five brilliant young minds from education, psychology, learning science, and survey methodology. They’ll share their innovative solutions to challenges, powered by AI and data science.

Exploring the NAEP Math Achievement Gap: Insights from Test-Taking Process Data

Dr. Susu Zhang, University of Illinois at Urbana-Champaign

The National Assessment of Educational Progress (NAEP) serves as a pivotal tool in monitoring the educational achievements and progress of U.S. students, thereby informing educational policy and resource distribution. Persistent disparities in math performance between students with disabilities and their peers have been documented through NAEP results. Recent initiatives by the Institute of Education Sciences, including the release of restricted-use process data from select NAEP math assessments and the funding of exploration grants, aim to investigate the relationship between test-taking behaviors and math performance among students with disabilities. The aim is to gather evidence that ultimately contributes to improving the educational outcome of these students with special needs. In this talk, I discuss several recent and ongoing projects that address this aim, by leveraging the new measurement opportunities brought by additional behavioral data collected from computerized tests beyond scores, known as process data. Specifically, students’ response times, test navigation and answer change trajectories, and the sequence of keystrokes and clickstreams, are used to test or generate initial hypotheses on factors (e.g., test design and accommodation, math skills or misconceptions) that contributed to the NAEP math outcome for students with disabilities.

This hybrid event will be offered virtually and in Beering Hall 1242.

View event recording: https://youtu.be/_zSWlyBsuQ8

Dr. Susu Zhang

About the Presenter

Dr. Susu Zhang is an Assistant Professor of Psychology and Statistics at the University of Illinois Urbana-Champaign (UIUC). Her research involves latent variable modeling for testing and learning data, as well as the integration of complex data (e.g., log data) into latent variable models to address measurement and educational questions. She currently serves as the PI/co-PI of two federal funded projects on the analysis of NAEP Mathematics process data to understand the performance gap between learners from different demographic groups. Her work has been published in major journals in the field (e.g., Psychometrika, British Journal of Mathematical and Statistical Psychology, Multivariate Behavioral Research, Computers in Human Behavior) and received the NCME 2022 Alicia Cascallar Award. In addition, she co-delivered several R packages and short courses for process data analysis and cognitive diagnostic assessments for learning.

Dr. Susu Zhang
Assistant Professor
Department of Psychology and Statistics
University of Illinois at Urbana Champaign

Contact: Hua-Hua Chang, chang606@purdue.edu