A Nonparametric Method for Assessment of Interactions in a Survival Analysis Regression Model Based on Right-Censored Data

• Activity Number: 352
• Type: Contributed
• Date/Time: Tuesday, August 6, 2013 : 10:30 AM to 12:20 PM
• Sponsor: Section on Nonparametric Statistics
• Author(s): MinJae Lee*+ and Mohammad Rahbar
• Companies: and Univ of Texas Health Science Center
• Keywords: Kaplan-Meier ; Survival Time ; Censoring ; Cox Proportional Hazard Model ; Interactions ; PROMMTT

Abstract

We propose a nonparametric method for assessment of interactions when we are concerned with investigation of the simultaneous effects of two or more factors in a regression model based on randomly right censored data. The proposed method allows for varying levels of censorship in the outcome among different groups of subjects at different levels of the independent variables. We present the asymptotic distribution of the estimators of the parameters in our model, which then allows for statistical inference. Through a simulation study we assess the effect of the censoring rate on the standard error of these types of estimators and power of our new proposed method with that of using the Cox Proportional Hazard (PH) model. Finally, we illustrate application of our proposed method to real life data to test an interaction effect between mechanism of injury and study sites using median time for a trauma patient to receive 3 units of red blood cells in Prospective Observational Multicenter Major Trauma Transfusion (PROMMTT) study. Our results indicate that when the assumption of PH is not met, our procedure performs better than the Cox model.