CAUSAL INFERENCE SEMINAR SERIES.

Miss(ing) Congeniality: The Cost of Incompatible Imputation Models Lucy D’Agostino McGowan, Associate Professor of Statistical Sciences, Wake Forest University Doubly robust estimators are often viewed as protected against model misspecification, but this protection can fail in the presence of missing data. When multiple imputation is used, lack of congeniality between the imputation and analysis models can induce bias even when both the propensity score and outcome models are correctly specified. Valid inference requires imputation models to include all variables from both the propensity score and outcome models, specified in compatible functional forms. Violations of these conditions can lead to substantial bias in treatment effect estimates. A general framework for combining multiple imputation with doubly robust estimation is presented, the conditions required for congeniality are characterized, and the consequences of misspecification are illustrated. The talk concludes with practical recommendations for specifying imputation models to preserve the validity of doubly robust methods in applied causal analyses. About the speaker Lucy D’Agostino McGowan is an associate professor in the Department of Statistical Sciences at Wake Forest University. She received her PhD in Biostatistics from Vanderbilt University and completed her postdoctoral training at Johns Hopkins University Bloomberg School of Public Health. Her research focuses on causal inference, statistical communication, analytic design theory, and data science pedagogy. Lucy can be found blogging at livefreeordichotomize.com, on bluesky @LucyStats, and podcasting on Casual Inference. Future seminars TBA for Fall 2026 About the BU causal inference seminar The BU causal inference seminar series is co-organized by the Biostatistics Department (Sara Lodi and Fatema Shafie Khorassani) and the Mathematics & Statistics Department (Judith Lok). Lunch at 12:30 (email fshafie@bu.edu to RSVP for lunch)