![Sample our Computer Science journals, sign in here to start your access, latest two full volumes FREE to you for 14 days]({"type":"image" , "src" : "/sda/5928/TOC-Subject-Sample-2021-Computer-Science.jpg"})
Abstract
Generalized estimating equations (GEE) approach has been used to estimate the parameters in semiparametric accelerated failure time (AFT) models with clustered and censored data. However, the working correlation model has a substantial impact on estimator efficiency when using the GEE method. This article proposes a general correlation model to incorporate the correlations among the clustered and censored data and protect against avoidable loss of efficiency associated with misspecified correlation structure. The proposed estimator is consistent and asymptotically normal. Simulation studies are carried out to demonstrate the effectiveness of the proposed method. Finally, a real dataset from a toxicology study is analyzed for illustration.
Additional information
Funding
Yan Zhou’s research was supported by the National Natural Science Foundation of China (Grant No. 11701385), the National Natural Science Foundation of China (Grant No. 11871411) and the Doctor Start Fund of Guangdong Province (Grant No. 2016A030310062). Liya Fu’s research was supported by the National Natural Science Foundation of China (11871390), the Fundamental Research Funds for the Central Universities (No. xjj2017180), the Natural Science Basic Research Plan in Shanxi Province of China (2018JQ1006).