Ji Seung Yang, University of Maryland
Leveraging Regression Discontinuity Analysis with Latent Variable Models
This talk focuses on the integration of latent variable modeling in regression discontinuity analysis, a popular quasi-experimental method in which treatment assignment is determined by a cutoff on an observed running variable. By integrating latent variable measurement models for both running variables and outcome variables into regression discontinuity analysis, the proposed approach allows researchers to examine heterogeneity of treatment effects at the observed cutoff arising from measurement error, assess the generalizability of effects beyond the cutoff, and optimize study designs to target specific treatment effects. Multilevel and multidimensional item response models are employed to accommodate cluster sampling and multiple running variables, as illustrated through an empirical example using state-level data from the United States.
About the Speaker
Dr. Yang is an Associate Professor of Quantitative Methodology: Measurement and Statistics (QMMS) Program in the Department of Human Development and Quantitative Methodology at the University of Maryland. She joined the QMMS faculty in Fall 2013, after completing a postdoctoral fellowship at the University of California, Los Angeles (UCLA). Dr. Yang earned her Ph.D. in 2012 from UCLA’s Social Research Methodology Program, with a specialization in Advanced Quantitative Methods in Educational Research, within the School of Education and Information Studies. She previously received her M.A. and B.A. in Education from Yonsei University in Korea.
Dr. Yang’s research focuses on measurement and advanced quantitative methods in the social sciences. Her work centers on (1) the development of statistical models that explicitly account for measurement error within frameworks such as Item Response Theory, Generalizability Theory, Hierarchical Linear Modeling, and latent variable modeling, and (2) the development of multilevel and multidimensional item response models with efficient computational approaches. Dr. Yang has received research funding from the Institute of Education Sciences, the National Institutes of Health, and the National Science Foundation to support her work on measurement and advanced quantitative methodology.