This paper described 2 statistical methods designed to correct for bias from exposure measurement error in point and interval estimates of relative risk.
The first method takes the usual point and interval estimates of the log relative risk obtained from logistic regression and corrects them for nondifferential measurement error using an exposure measurement error model estimated from validation data.
The second, likelihood-based method fits an arbitrary measurement error model suitable for the data at hand and then derives the model for the outcome of interest.
Data from Valanis and colleagues'study of the health effects of antineoplastics exposure among hospital pharmacists were used to estimate the prevalence ratio of fever in the previous 3 months from this exposures.
For an interdecile increase in weekly number of drugs mixed, the prevalence ratio, adjusted for confounding, changed from 1.06 to 1.17 (95% confidence interval [CI]=1.04,1.26) after correction for exposure measurement error.
Exposure measurement error is ofter an important source of bias in public health research.
Methods are available to correct such biases.
Mots-clés Pascal : Anticancéreux, Exposition professionnelle, Pharmacien, Personnel sanitaire, Erreur mesure, Biais méthodologique, Correction erreur, Méthode statistique, Homme, Milieu hospitalier, Méthodologie
Mots-clés Pascal anglais : Antineoplastic agent, Occupational exposure, Chemist, Health staff, Measurement error, Methodological bias, Error correction, Statistical method, Human, Hospital environment, Methodology
Notice produite par :
Inist-CNRS - Institut de l'Information Scientifique et Technique
Cote : 98-0196264
Code Inist : 002B30A01A1. Création : 11/09/1998.