On a Shape-Invariant Hazard Regression Model

Abstract: In survival analysis, Cox model is widely used for most clinical trial data. Alternatives include the additive hazard model, the accelerated failure time (AFT) model and a more general transformation model. All these models assume that the effects for all covariates are on the same scale. However, it is possible that for different covariates, the effects are on different scales. In this paper, we propose a shape-invariant hazard regression model that allows us to estimate the multiplicative treatment effect with adjustment of covariates that have non-multiplicative effects. We propose moment-based inference procedures for the regression parameters. We also discuss the risk prediction and goodness of fit test for our proposed model. Numerical studies show good finite sample performance of our proposed estimator. We applied our method to Veteran's Administration (VA) lung cancer data and the HIVNET 012 data. For the latter, we found that single-dose nevirapine treatment has a significant improvement for 18-month survival with appropriate adjustment for maternal CD4 counts and virus load.