Tuesday, October 15, 2024
2:00 - 4:00 PM (PDT) at Berkeley Way West 1207 and via Zoom
Open to GSE faculty, students, and community.
Request a zoom link from convenors@bear.berkeley.edu
Abstract:
The main focus of this talk is on Lord’s paradox within the latent variable modeling framework. Lord (1967) describes a hypothetical paradox in which two researchers, analyzing the same dataset using different but defensible methods, come to very different conclusions about the effects of an intervention on outcomes. Lord’s paradox has re-emerged in many causal inference settings today around the issue of when it is appropriate to control for baseline status. This talk will discuss two main approaches for analyzing such data: (1) to regress the change from pretest to posttest on the treatment indicator, and (2) to regress the posttest on the treatment indicator and pretest. The talk will show how these two approaches can yield conflicting results—hence the paradox. We will elaborate on how approaches can be reconciled, depending on the context, and provide examples from the BEAR Center’s ADM project.
About the authors:
Perman Gochyyev is currently a Statistical Project Leader at Sanofi, where he conducts research at the intersection of biostatistics and quantitative psychometrics. Before joining Sanofi, he served as a research psychometrician at the University of California, Berkeley, and at the Berkeley Evaluation and Assessment Research Center. Perman earned his Ph.D. in Quantitative Methods and Evaluation from UC Berkeley in 2015. His research primarily focuses on latent variable and multilevel modeling, multidimensional and ordinal Item Response Theory (IRT) models, latent class models, and issues related to causal inference.
Mark Wilson is a Distinguished Professor of Education at the University of California, Berkeley, and also a Professor at the University of Melbourne. He received his PhD degree from the University of Chicago in 1984. His interests focus on measurement and applied statistics, and he has published 175 refereed articles in those areas, 78 invited chapters in edited books, and 17 books. He was elected president of the Psychometric Society, and, more recently president of the US National Council on Measurement in Education (NCME); he is also a Member of the US National Academy of Education, a Fellow of the American Educational Research Association, and the American Psychological Association, and also a National Associate of the US National Research Council. He is the Director of the Berkeley Evaluation and Assessment Research (BEAR) Center. His research and development interests focus on establishing a framework for measurement practice informed by the philosophy of measurement, statistical models aligned with scientific models of the construct, and instruments to measure new constructs.