Title: Collaborative-controlled LASSO for constructing propensity score-based estimators in high-dimensional data
Authors: Cheng Ju - University of California Berkeley (United States)
Richard Wyss - Brigham and Womens Hospital and Harvard Medical School (United States)
Jessica M Franklin - Brigham and Womens Hospital and Harvard Medical School (United States)
Sebastian Schneeweiss - Brigham and Womens Hospital and Harvard Medical School (United States)
Jenny Haggstrom - Umea University (Sweden) [presenting]
Mark van der Laan - University of California at Berkeley (United States)
Abstract: Propensity score (PS) based estimators are increasingly used for causal inference in observational studies. However, model selection for PS estimation in high-dimensional data has received little attention. In these settings, PS models have traditionally been selected based on the goodness-of-fit for the treatment mechanism itself, without consideration of the causal parameter of interest. Collaborative minimum loss-based estimation (C-TMLE) is a novel methodology for causal inference that takes into account information on the causal parameter of interest when selecting a PS model. This ``collaborative learning'' considers variable associations with both treatment and outcome when selecting a PS model in order to minimize a bias-variance trade off in the estimated treatment effect. We introduce a novel approach for collaborative model selection when using the LASSO estimator for PS estimation in high-dimensional covariate settings. To demonstrate the importance of selecting the PS model collaboratively, we designed quasi-experiments based on a real electronic healthcare database, where only the potential outcomes were manually generated, and the treatment and baseline covariates remained unchanged. Results showed that the C-TMLE algorithm outperformed other competing estimators for both point estimation and confidence interval coverage.