Cargando…

Corrected likelihood for proportional hazards measurement error model and its application.

Consider the case where the exact values of covariates in the proportional hazards model may not be observed but instead, only surrogates for them involving measurement errors are available. The maximum likelihood estimate based on the partial likelihood with the true covariate replaced by the obser...

Descripción completa

Detalles Bibliográficos
Autores principales: Nakamura, T, Akazawa, K
Formato: Texto
Lenguaje:English
Publicado: 1994
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC1566550/
https://www.ncbi.nlm.nih.gov/pubmed/7851326
_version_ 1782129643559583744
author Nakamura, T
Akazawa, K
author_facet Nakamura, T
Akazawa, K
author_sort Nakamura, T
collection PubMed
description Consider the case where the exact values of covariates in the proportional hazards model may not be observed but instead, only surrogates for them involving measurement errors are available. The maximum likelihood estimate based on the partial likelihood with the true covariate replaced by the observed surrogate is even asymptotically biased and may cause seriously misleading results in covariance analysis based on the partial likelihood. These facts are illustrated by Monte Carlo simulation. A correction to partial likelihood proposed by the first author is studied to gain insight into its merits and limitations in practical applications. The results indicate that when the "effective magnitude of the measurement error" as defined in this article is small, which is indeed the case for most applications, the method will be useful. Some other correction methods for the measurement error in censored survival models are also reviewed and discussed.
format Text
id pubmed-1566550
institution National Center for Biotechnology Information
language English
publishDate 1994
record_format MEDLINE/PubMed
spelling pubmed-15665502006-09-19 Corrected likelihood for proportional hazards measurement error model and its application. Nakamura, T Akazawa, K Environ Health Perspect Research Article Consider the case where the exact values of covariates in the proportional hazards model may not be observed but instead, only surrogates for them involving measurement errors are available. The maximum likelihood estimate based on the partial likelihood with the true covariate replaced by the observed surrogate is even asymptotically biased and may cause seriously misleading results in covariance analysis based on the partial likelihood. These facts are illustrated by Monte Carlo simulation. A correction to partial likelihood proposed by the first author is studied to gain insight into its merits and limitations in practical applications. The results indicate that when the "effective magnitude of the measurement error" as defined in this article is small, which is indeed the case for most applications, the method will be useful. Some other correction methods for the measurement error in censored survival models are also reviewed and discussed. 1994-11 /pmc/articles/PMC1566550/ /pubmed/7851326 Text en
spellingShingle Research Article
Nakamura, T
Akazawa, K
Corrected likelihood for proportional hazards measurement error model and its application.
title Corrected likelihood for proportional hazards measurement error model and its application.
title_full Corrected likelihood for proportional hazards measurement error model and its application.
title_fullStr Corrected likelihood for proportional hazards measurement error model and its application.
title_full_unstemmed Corrected likelihood for proportional hazards measurement error model and its application.
title_short Corrected likelihood for proportional hazards measurement error model and its application.
title_sort corrected likelihood for proportional hazards measurement error model and its application.
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC1566550/
https://www.ncbi.nlm.nih.gov/pubmed/7851326
work_keys_str_mv AT nakamurat correctedlikelihoodforproportionalhazardsmeasurementerrormodelanditsapplication
AT akazawak correctedlikelihoodforproportionalhazardsmeasurementerrormodelanditsapplication