JSM 2015 Preliminary Program

Online Program Home
My Program

Abstract Details

Activity Number: 441
Type: Contributed
Date/Time: Tuesday, August 11, 2015 : 2:00 PM to 3:50 PM
Sponsor: Social Statistics Section
Abstract #316764
Title: Modified Peters-Belson: Bias in Treatment-Prognostic Score Interaction
Author(s): Josh Errickson*
Companies: University of Michigan
Keywords: Causal Inference ; Peters-Belson ; Bias ; Estimating Equations ; Sandwich Estimator ; Robust
Abstract:

Recent papers in empirical economics (Gine et al. (2012), Dynarski et al. (2011), and others) have been interested in examining if a treatment has more effect among those who are predicted to have the worst response in the absence of any treatment. They approach this question by using a two-stage Peters-Belson type estimator, studying the interaction between the treatment and some prognostic score. The statistical validity of this method has not been verified. There has been some work showing simulationally that this method introduces bias. We offer a correction to this, both in the form of a corrected confidence interval and a point estimate that minimizes the bias, as well as examining the statistical properties of this method.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2015 program





For program information, contact the JSM Registration Department or phone (888) 231-3473.

For Professional Development information, contact the Education Department.

The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.

2015 JSM Online Program Home