Abstract: Studying causal effects of continuous treatments is important for gaining a deeper understanding of many interventions, policies, or medications, yet researchers are often left with observational studies for doing so. In the observational setting, confounding is a barrier to the estimation of causal effects. Weighting approaches seek to control for confounding by reweighting samples so that confounders are comparable across different treatment values. Yet, for continuous treatments, weighting methods are highly sensitive to model misspecification. In this talk, we elucidate the key property that makes weights effective in estimating causal quantities involving continuous treatments. We show that to eliminate confounding, weights should make treatment and confounders independent on the weighted scale. We develop a measure that characterizes the degree to which a set of weights induces such independence. Further, we propose a new model-free method for weight estimation by optimizing our measure. We study the theoretical properties of our measure and our weights, and prove that our weights can explicitly mitigate treatment-confounder dependence. The empirical effectiveness of our approach is demonstrated in a suite of challenging numerical experiments, where we find that our weights are quite robust and work well under a broad range of settings. Lastly, in an ongoing work, we also utilize new theoretical approaches for showing uniform convergence of our optimization-based weights to the true weights.
Bio: Guanhua Chen, Ph.D. is an Associate Professor in the Department of Biostatistics and Medical Informatics at the University of Wisconsin–Madison. He earned his Ph.D. in Biostatistics from the University of North Carolina at Chapel Hill and his B.S. in Bioinformatics from Huazhong University of Science and Technology. Dr. Chen’s research focuses on developing advanced statistical learning and causal inference methods to advance precision medicine, with applications spanning high-dimensional biomedical data such as genomics, microbiome, electronic health records, and other complex health datasets. Dr. Chen has served as principal investigator on multiple projects funded by the National Institutes of Health (NIH), the National Science Foundation (NSF), and the Patient-Centered Outcomes Research Institute (PCORI), with total funding exceeding five million USD. He has published nearly one hundred papers in leading journals, including Journal of the American Statistical Association, Biometrika, Biostatistics, Biometrics, Bioinformatics, Genome Biology, and Journal of American Medical Informatics Association.
