Speaker

Dr. Susu Zhang
Joint Assistant Professor of Psychology and Statistics
University of Illinois Urbana-Champaign

Dr. Susu Zhang received her PhD Quantitative Psychology from University of Illinois Urbana-Champaign in 2018, concurrently completing an MS in Applied Math. She was a post doc at the Department of Statistics at Columbia University from 2018-2020 before returning to UIUC as a joint Assistant Professor of Psychology and Statistics. Broadly, her research addresses the use of latent variable modeling, statistical/machine learning, and other quantitative methods to solve practical problems in educational and psychological testing. She has over 30 publications on these topics, in journals including SEM, MBR, and Psychometrika. Her work on the analysis of complex data (e.g., log data) in testing and learning environments has been funded by AERA / NSF and IES, and received the Alicia Cascallar Award from NCME in 2022.

Title

Informing Educational Measurement with Test-Taking Process Data

Abstract

Computerized testing affords the collection of additional behavioral data beyond scores on test questions. One such instance is process data, the computer-recorded log files generated from test-taker interactions with a computerized assessment, e.g., keystrokes and clickstreams, in pursuit of solving a problem. This type of data offers rich insights into the cognitive processes underlying problem-solving, opening new avenues to address existing measurement and educational questions and explore novel ones. However, like constructed responses on open-ended questions with infinitely possible answers of different lengths, process data are highly unstructured and often noisy. This precludes the direct application of many well-established tools and psychometric models for structured test response data. In this talk, I discuss how sequential features extracted from test-taking process data can be incorporated into latent variable modeling frameworks commonly used in educational measurement, to address common questions in measurement and educational research, such as improving score reliability and understanding the math performance gap between demographic groups.