- This event has passed.
Webinar: Biostatistics and Bioinformatics Seminar – “Variance Reduction in Inverse Probability Weighted Estimators for the Average Treatment Effect Using Propensity Score”
January 14, 12:00 pm to 1:00 pm
“Variance Reduction in Inverse Probability Weighted Estimators for the Average Treatment Effect Using Propensity Score” will be presented by Jiangang “Jason” Liao, PhD, Professor and Chief, Division of Biostatistics and Bioinformatics, Department of Public Health Sciences, Penn State College of Medicine.
Propensity methodology (Rosenbaum & Rubin, 1983) is widely used in medical research to compare different treatments in designs with a non-randomized treatment allocation. The inverse probability weighted (IPW) estimators are a primary tool for estimating the average treatment effect but the large variance of these estimators is often a significant concern for their reliable use in practice. Inspired by Rao-Blackwellization, this paper proposes a smoothed version of any IPW estimator as its averages over a distribution of the treatment assignment determined by the propensity scores.
In this simulation study, a smoothed IPW estimator achieves a substantial variance reduction over its original version with only a small increased bias, for example two- to seven-fold variance reduction for the three IPW estimators in (Lunceford & Davidian, 2004). The smoothed version of their first IPW estimator is recommended for general use due to its smaller variance and bias. An implementation in R is provided.
Participants may also join by calling 929-205-6099, meeting ID 322 043 373. If prompted, enter passcode 167660.