Title: Meta-Reanalysis: A Research Design for Generalized Social Scientific Inferences
By Alexander Coppock, Associate Professor of Political Science and IPR Fellow
Abstract: Studying the generalizability of empirical claims involves conducting the same study many times in multiple contexts, but our political science does not typically generate empirical evidence of this kind due to novelty pressures. Meta-reanalysis is a research design in which we obtain original study data sets, isolate the common estimands, re-analyze each study to estimate those estimands, and then meta-analyze the resulting estimates. Meta-reanalysis represents a path forward for studying generalizability because of the almost unintentional replications embedded in the extant empirical record. The meta-scientific implication of this work is that, in order to improve the discipline’s position on the novelty–generalizability tradeoff, it will have to study fewer empirical questions in more contexts.
This event is part of the Fay Lomax Cook Winter 2026 Colloquium Series, where our researchers from around the University share their latest policy-relevant research.
Please note all colloquia this quarter will be held in-person only.