Testing based on sampled data for proportional hazards model

Autor:	Pawel Marzec, Leszek Marzec
Rok vydání:	1998
Předmět:	Statistics and Probability Counting process Goodness of fit Stochastic process Proportional hazards model Statistics Covariate Econometrics Asymptotic distribution Estimator Statistics Probability and Uncertainty Martingale (probability theory) Mathematics
Zdroj:	Statistics & Probability Letters. 37:303-313
ISSN:	0167-7152
DOI:	10.1016/s0167-7152(97)84157-0
Popis:	Borgan et al. (1995) developed the asymptotic theory based on cohort sampling for the general Cox proportional hazards model of Andersen and Gill (1982). Under the model adequacy they proved the consistency and asymptotic normality of the maximum partial likelihood estimator defined subject to the covariate information on case-control subsample of the full-cohort data. The estimator has many potential applications in practice (Borgan and Langholz, 1993). In this paper we propose a test for checking the model adequacy under the above limitation concerning the covariate information available. The test is based on the modified version of the martingale-residual type stochastic process of Marzec and Marzec (1997) for the full-cohort data.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::231c901c9cf87d2f6d87b3cabdfa610b https://doi.org/10.1016/s0167-7152(97)84157-0 Zobrazit plný text záznamu Full Text from ScienceDirect