Machine learning outcome regression improves doubly robust estimation of average causal effects.

Journal: Pharmacoepidemiology and drug safety
Published Date:

Abstract

BACKGROUND: Doubly robust estimation produces an unbiased estimator for the average treatment effect unless both propensity score (PS) and outcome models are incorrectly specified. Studies have shown that the doubly robust estimator is subject to more bias than the standard weighting estimator when both PS and outcome models are incorrectly specified.

Authors

  • Byeong Yeob Choi
    Department of Population Health Sciences, UT Health San Antonio, San Antonio, Texas, USA.
  • Chen-Pin Wang
    University of Texas Health Science Center, San Antonio, TX, U.S.A.
  • Jonathan Gelfond
    Department of Population Health Sciences, UT Health San Antonio, San Antonio, Texas, USA.