Imputation for semiparametric transformation model

Authors: Hao Liu Jing Qin Yu Shen

Publish Date: 2012/08/18

Volume: 18, Issue: 4, Pages: 470-503

PDF Link

Abstract

Widely recognized in many fields including economics engineering epidemiology health sciences technology and wildlife management lengthbiased sampling generates biased and rightcensored data but often provide the best information available for statistical inference Different from traditional rightcensored data lengthbiased data have unique aspects resulting from their sampling procedures We exploit these unique aspects and propose a general imputationbased estimation method for analyzing lengthbiased data under a class of flexible semiparametric transformation models We present new computational algorithms that can jointly estimate the regression coefficients and the baseline function semiparametrically The imputationbased method under the transformation model provides an unbiased estimator regardless whether the censoring is independent or not on the covariates We establish largesample properties using the empirical processes method Simulation studies show that under small to moderate sample sizes the proposed procedure has smaller mean square errors than two existing estimation procedures Finally we demonstrate the estimation procedure by a real data example

Keywords: