Three paths to equality: Causal decomposition of group disparities – Prof. Felix Elwert

Join us for the Data Sciences Speaker Series with Prof. Felix Elwert, University of Wisconsin-Madison. This talk is co-sponsored by the Data Sciences Institute and the Department of Sociology, University of Toronto Scarborough.

Registration Required – REGISTER HERE

• Date: January 27, 2025
• Time: 11:00 a.m. – 12:00 p.m.
• Format: In-person
• Location: Data Sciences Institute, 10th-floor Seminar Room, 700 University Avenue, Toronto 

Three paths to equality: Causal decomposition of group disparities

Description:
We introduce a new nonparametric causal decomposition approach that identifies the mechanisms by which a treatment variable contributes to a group-based outcome disparity. Examples include the causal roles of education in generating gender wage gaps, racial health disparities, and intergenerational income persistence. Our approach distinguishes three mechanisms that operate, respectively, via group differences in 1) treatment prevalence, 2) average treatment effects, and 3) selection into treatment based on individual-level treatment effects. Our approach reformulates classic Kitagawa-Blinder-Oaxaca decompositions in causal and nonparametric terms, complements causal mediation analysis by explaining group disparities instead of group effects, and isolates conceptually distinct mechanisms conflated in recent random equalization decompositions. In contrast to all prior approaches, our framework uniquely identifies differential selection into treatment as a novel disparity-generating mechanism. (Joint work with Ang Yu).

Biography
Prof. Felix Elwert’s research focuses on social inequality, social demography, and applied statistics. He develops methods of causal inference and investigates the contextual drivers of inequality, income, education, and health. Prof. Elwert collaborates with global teams to conduct large-scale randomized experiments, mine population registers, and analyze surveys, constantly seeking ways to establish causality from data.

He received multiple awards from the American Sociological Association and the American Statistical Association. His work has appeared in the American Journal of Sociology, the American Review of Sociology, Sociological Science, Demography, and JAMA and other high-impact Journals.

He graduated from Harvard University in 2007 with degrees in sociology and statistics. Prof. Elwert has taught applied causal inference at prestigious institutions including Berkeley, Princeton, and Columbia, as well as in Berlin, Budapest, and Copenhagen. From 2014 to 2016, he served as the Karl W. Deutsch Professor and Acting Director of Social Inequality and Social Policy at the WZB Berlin Social Center. Currently, he is a Professor of Sociology and Biostatistics at the University of Wisconsin-Madison and serves as the Editor-in-Chief of Sociological Methods & Research.