Regression analysis of multivariate current status data with auxiliary covariates under the additive hazards model

• Published in: Computational statistics & data analysis Vol. 87; pp. 34 - 45
• Main Authors: Chen, Yurong, Feng, Yanqin, Sun, Jianguo
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.07.2015
• Subjects: Additives; Auxiliary covariates; Data processing; Estimators; Failure times; Hazards; Interval-censored data; Partial likelihood function; Regression; Regression analysis; Statistics; Validation sample; Interval-censored data; Validation sample; Auxiliary covariates; Partial likelihood function
• ISSN: 0167-9473; 1872-7352
• DOI: 10.1016/j.csda.2015.01.005

In a biomedical study, it often occurs that some covariates of interest are not measured exactly and only some auxiliary information on them is available. In this case, a question of interest is how to make use of the available auxiliary information for statistical analysis. This paper discusses this problem in the context of regression analysis of multivariate current status failure time data arising from the additive hazards model. More specifically, we consider the situation where the covariates of interest are assessed only for the subjects in a validation set and a continuous auxiliary covariate is available for all subjects. For the problem, by employing the marginal model approach, we propose two procedures for estimation of regression parameters. The methods can be easily implemented and the asymptotic properties of the resulting estimators are established. Also an extensive simulation study is conducted for the evaluation of the proposed methods and indicates that they work well in practice. An illustrative example is provided.