A1193
Title: Semiparametric methods for left-truncated and right-censored survival data with covariate measurement error
Authors: Grace Yi - University of Western Ontario (Canada) [presenting]
Abstract: Biased samples caused by left-truncation (or length-biased sampling) and measurement error often accompany survival analysis. While such data frequently arise in practice, little work has been available to address these features simultaneously. Valid inference methods are explored for handling left-truncated and right-censored survival data with measurement error under the widely used Cox model. First, a flexible estimator is exploited for the survival model parameters, which does not require the specification of the baseline hazard function. An augmented nonparametric maximum likelihood estimator is further developed to improve efficiency. Asymptotic results are established, and the efficiency and robustness issues for the proposed estimators are examined. The proposed methods enjoy appealing features in that the distributions of the covariates and the truncation times are left unspecified. Numerical studies are reported to assess the finite sample performance of the proposed methods.