Lifetime Data Analysis

, Volume 15, Issue 1, pp 120–146

Evaluating bias correction in weighted proportional hazards regression


DOI: 10.1007/s10985-008-9102-4

Cite this article as:
Pan, Q. & Schaubel, D.E. Lifetime Data Anal (2009) 15: 120. doi:10.1007/s10985-008-9102-4


Often in observational studies of time to an event, the study population is a biased (i.e., unrepresentative) sample of the target population. In the presence of biased samples, it is common to weight subjects by the inverse of their respective selection probabilities. Pan and Schaubel (Can J Stat 36:111–127, 2008) recently proposed inference procedures for an inverse selection probability weighted (ISPW) Cox model, applicable when selection probabilities are not treated as fixed but estimated empirically. The proposed weighting procedure requires auxiliary data to estimate the weights and is computationally more intense than unweighted estimation. The ignorability of sample selection process in terms of parameter estimators and predictions is often of interest, from several perspectives: e.g., to determine if weighting makes a significant difference to the analysis at hand, which would in turn address whether the collection of auxiliary data is required in future studies; to evaluate previous studies which did not correct for selection bias. In this article, we propose methods to quantify the degree of bias corrected by the weighting procedure in the partial likelihood and Breslow-Aalen estimators. Asymptotic properties of the proposed test statistics are derived. The finite-sample significance level and power are evaluated through simulation. The proposed methods are then applied to data from a national organ failure registry to evaluate the bias in a post-kidney transplant survival model.


Breslow-Aalen estimatorConfidence bandsInverse-selection-probability weightsObservational studiesProportional hazards modelSelection biasWald test

Copyright information

© Springer Science+Business Media, LLC 2008

Authors and Affiliations

  1. 1.Department of StatisticsGeorge Washington UniversityWashingtonUSA
  2. 2.Department of BiostatisticsUniversity of MichiganAnn ArborUSA