Multivariate failure time data arise frequently in survival analysis.A commonly used tech-nique is the working independence estimator for marginal hazard models.Two natural questions are how to improve the effciency of the working independence estimator and how to identify the situations under which such an estimator has high statistical effciency.In this paper,three weighted estimators are proposed based on three different optimal criteria in terms of the asymptotic covariance of weighted estimators.Simplifiedclose-form solutions are found,which always outperform the working indepen-dence estimator.We also prove that the working independence estimator has high statistical effciency,when asymptotic covariance of derivatives of partial log-likelihood functions is nearly exchangeable or diagonal.Simulations are conducted to compare the performance of the weighted estimator and work-ing independence estimator.A data set from Busselton population health surveys is analyzed using the proposed estimators.
FAN JianQing1,2,ZHOU Yong2,3,CAI JianWen4 & CHEN Min3 1 Department of Operations Research and Financial Engineering,Princeton University,Princeton,NJ08544,USA 2 Department of Statistics,Shanghai University of Finance and Economics,Shanghai 200433,China 3 Institute of Applied Mathematics,Academy of Mathematics and Systems Science,Chinese Academy of Sci-ences,Beijing 100190,China 4 Department of Biostatistics,University of North Carolina at Chapel Hill,Chapel Hill,NC 27599-7420,USA
