Weighted Cumulative Treatment Estimation for Sequentially Randomized Clinical Trials in the Presence of Nonproportional Hazards

• Activity Number: 569
• Type: Contributed
• Date/Time: Wednesday, August 3, 2011 : 2:00 PM to 3:50 PM
• Sponsor: Biometrics Section
• Author(s): Xinyu Tang*+ and Adbus S. Wahed
• Companies: University of Arkansas for Medical Sciences and University of Pittsburgh
• Keywords: non-proportional hazards ; cumulative baseline hazard ; stratified proportional hazard model ; treatment regime

Abstract

Proportional hazards model is widely used in survival analysis to adjust for baseline covariates. Although Lokhnygina and Helterbrand (2007) introduced Cox regression methods for two-stage randomization designs, their method can only be applied to test the equality of two treatment regimes that share the same maintenance therapy. Moreover, their method does not allow auxiliary variables to be included in the model. Besides, in many medical studies, the treatment effect is not constant over time. Wei and Schaubel (2008) proposed an estimator of cumulative treatment effects based on treatment-specific cumulative baseline hazards using a stratified proportional hazards model. Their model assumed proportionality within treatment group and non-proportionality across treatment groups. We propose a similar approach to estimate the cumulative treatment effect for treatment regimes from sequentially randomized clinical trials. Comparisons among treatment regimes are performed by testing the ratio of the estimated cumulative hazards. A simulation study was conducted to evaluate the performance of the estimators and proposed tests.