Premium
Testing goodness‐of‐fit for the proportional hazards model based on nested case–control data
Author(s) -
Lu Wenbin,
Liu Mengling,
Chen YiHau
Publication year - 2014
Publication title -
biometrics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 2.298
H-Index - 130
eISSN - 1541-0420
pISSN - 0006-341X
DOI - 10.1111/biom.12239
Subject(s) - resampling , statistics , goodness of fit , mathematics , computer science
Summary Nested case–control sampling is a popular design for large epidemiological cohort studies due to its cost effectiveness. A number of methods have been developed for the estimation of the proportional hazards model with nested case–control data; however, the evaluation of modeling assumption is less attended. In this article, we propose a class of goodness‐of‐fit test statistics for testing the proportional hazards assumption based on nested case–control data. The test statistics are constructed based on asymptotically mean‐zero processes derived from Samuelsen's maximum pseudo‐likelihood estimation method. In addition, we develop an innovative resampling scheme to approximate the asymptotic distribution of the test statistics while accounting for the dependent sampling scheme of nested case–control design. Numerical studies are conducted to evaluate the performance of our proposed approach, and an application to the Wilms' Tumor Study is given to illustrate the methodology.