报告人：Bo Lu, Division of Biostatistics, College of Public Health, The Ohio State University
报告题目：Propensity Score Adjustment for Estimating Population Causal Effect with Unequal Weights
报告摘要：Complex surveys are major sources of data for policy planning and program evaluation. However, literature on how to appropriately conduct causal inference using complex survey data is scarce. Propensity score based adjustments are popular in analyzing observational data. Ad-hoc propensity score adjustment incorporating survey weights have been used with complex survey data, without rigorous justification. In this talk, we propose a super population framework, which includes a pair of potential outcomes for every unit in the population, to streamline the propensity score analysis for complex survey data. Based on the proposed framework, we develop propensity score stratification and weighting estimators and the corresponding variance estimators that adjust for survey design features. Additionally, we argue that in this context we should estimate the propensity scores by a weighted logistic regression using the sampling weights. Various estimators are compared in a simulation study, which shows that the proposed estimators perform well when treatment effects are heterogeneous. As the treatment effect becomes more heterogeneous, the gains of adjusting for the survey design get bigger. This work is motivated by the research on evaluating the impact of Affordable Care Act on individual health outcomes using Ohio Medicaid Assessment Survey (2012).