In many observational cohort studies, a pair of correlated event times are usually observed for each individual. This paper develops a new approach for the semiparametric linear transformation model to handle the bivariate survival data under both truncation and censoring. By incorporating truncation, the potential referral bias in practice is taken into account. A class of generalised estimating equations are proposed to obtain unbiased estimates of the regression parameters. Large sample properties of the proposed estimator are provided. Simulation studies under different scenarios and analyses of real-world datasets are conducted to assess the performance of the proposed estimator.
Linear transformation models for censored data under truncation
RESTAINO, MARIALUISA;
2018
Abstract
In many observational cohort studies, a pair of correlated event times are usually observed for each individual. This paper develops a new approach for the semiparametric linear transformation model to handle the bivariate survival data under both truncation and censoring. By incorporating truncation, the potential referral bias in practice is taken into account. A class of generalised estimating equations are proposed to obtain unbiased estimates of the regression parameters. Large sample properties of the proposed estimator are provided. Simulation studies under different scenarios and analyses of real-world datasets are conducted to assess the performance of the proposed estimator.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
