Bias in the estimation of causal effects is a function of distributional imbalance of covariates between treatment groups. This talk introduces a novel weighting method explicitly designed to balance weighted covariate distributions, thus targeting the source of bias. This weighting strategy provides a model- free and tuning parameter- free approach for causal comparisons. It can be flexibly utilized in a wide variety of downstream causal analyses, such as the estimation of average treatment effects, individualized treatment rules and more.
Speaker: Jared Huling, PhD, Assistant Professor of Biostatistics, University of Minnesota School of Public Health
To obtain Zoom link please email: [email protected]