“Learning Under Random Distributional Shifts,” Kirk Bansak, UC Berkeley
QUANTITATIVE RESEARCH METHODS WORKSHOP
Abstract: Many existing approaches for generating predictions in settings with distribution shift model distribution shifts as adversarial or low-rank in suitable representations. In various real-world settings, however, we might expect shifts to arise through the superposition of many small and random changes in the population and environment. Thus, we consider a class of random distribution shift models that capture arbitrary changes in the underlying covariate space, and dense, random shocks to the relationship between the covariates and the outcomes. In this setting, we characterize the benefits and drawbacks of several alternative prediction strategies: the standard approach that directly predicts the long-term outcome of interest, the proxy approach that directly predicts a shorter-term proxy outcome, and a hybrid approach that utilizes both the long-term policy outcome and (shorter-term) proxy outcome(s). We show that the hybrid approach is robust to the strength of the distribution shift and the proxy relationship. We apply this method to datasets in two high-impact domains: asylum-seeker assignment and early childhood education. In both settings, we find that the proposed approach results in substantially lower mean-squared error than current approaches.
Kirk Bansak is an Assistant Professor in the Department of Political Science at UC Berkeley. His research interests are in causal inference, experimental design and analysis, refugee resettlement and asylum politics, algorithmic decision-making, and public opinion. He is the inaugural Faculty Director of the Yardi Scholarship at UC Berkeley, a faculty affiliate of the Immigration Policy Lab at Stanford University and ETH Zurich, and a faculty affiliate of the Berkeley Interdisciplinary Migration Initiative (BIMI). His research has appeared in Science, Nature, American Political Science Review, Journal of Politics, Political Analysis, Statistical Science, Journal of the Royal Statistical Society: Series A, Nature Human Behaviour, PNAS Nexus, Political Science Research and Methods, Legislative Studies Quarterly, and the ACM Conference on Economics and Computation (EC).
This workshop is open to the Yale community. To receive announcements and invitations to attend, please subscribe at https://csap.yale.edu/american-comparative-political-behavior-workshop.
The series is sponsored by the ISPS Center for the Study of American Politics and The Whitney and Betty MacMillan Center for International and Area Studies at Yale with support from the Edward J. and Dorothy Clarke Kempf Fund.