Power calculation for a score test in the dependent censoring model.

We propose a method for testing the assumption of independent censoring in right censored survival data. This method includes extra data collection by the subsequent follow-up of a subset of censored subjects. A score test statistic is derived within the framework of a Cox proportional hazards model with a time-dependent covariate. In this paper we focus on the power calculation for the score test under proportional hazards alternatives. Comparison of the observed with the theoretical power shows that the latter is somewhat lower than the former.