Statistics and Its Interface

Volume 13 (2020)

Number 2

Additive hazards regression for case-cohort studies with interval-censored data

Pages: 181 – 191

DOI: https://dx.doi.org/10.4310/SII.2020.v13.n2.a4

Authors

Mingyue Du (Center for Applied Statistical Research, School of Mathematics, Jilin University, Changchun, China)

Huiqiong Li (Department of Statistics, Yunnan University, Kunming, China)

Jianguo Sun (Department of Statistics, University of Missouri, Columbia, Mo., U.S.A.)

Abstract

A large literature has been developed for the analysis of case-cohort studies that are often performed with the aim of reducing the cost on the collection of covariate information. In particular, many authors have discussed their regression analysis under the framework of the additive hazards model, which is often preferred when the risk difference is of main interest. However, all of the existing methods assume or are applicable only to right-censored data. In this paper, we consider the case of interval-censored data, which often occur in practice and include right-censored data as a special case, and propose two estimation approaches, an estimating equation-based method and a maximum likelihood method. The resulting estimators of regression parameters are shown to be consistent and asymptotically normal. Also a simulation study is conducted and suggests that the proposed methods works well in practice, and an application is provided.

Keywords

additive hazards model, casecohort design, interval censoring, sieve estimation

The research of Huiqiong Li was partially supported by a grant from the Natural Science Foundation of China (11561075) and a grant from reserve talents for academic and technical leaders of middle-aged and young people in Yunnan Province (2017HB004).

Received 11 May 2019

Received revised 25 September 2019

Accepted 25 September 2019