In a logistic regression model when covariates are subject to measurement error the naive estimator, obtained by regressing on the observed covariates, is asymptotically biased. We introduce a bias-adjusted estimator and two estimators appropriate for normally distributed measurement errors -a functional maximum likelihood estimator and an estimator which exploits the consequences of sufficiency. The four proposals are studied asymptotically under conditions which are appropriate when the measurement error is small. A small Monte Carlo study illustrates the superiority of the measurement-error estimators in certain situations.
Publié le : 1985-12-14
Classification:
Errors-in-variables,
functional maximum likelihood,
logistic regression,
measurement error,
sufficiency,
62J05,
62H25
@article{1176349741,
author = {Stefanski, Leonard A. and Carroll, Raymond J.},
title = {Covariate Measurement Error in Logistic Regression},
journal = {Ann. Statist.},
volume = {13},
number = {1},
year = {1985},
pages = { 1335-1351},
language = {en},
url = {http://dml.mathdoc.fr/item/1176349741}
}
Stefanski, Leonard A.; Carroll, Raymond J. Covariate Measurement Error in Logistic Regression. Ann. Statist., Tome 13 (1985) no. 1, pp. 1335-1351. http://gdmltest.u-ga.fr/item/1176349741/