Miscellanea. Comparison of case-control to full cohort analyses under model misspecification
| Autor: | Ah Xiang, B Langholz |
|---|---|
| Rok vydání: | 1999 |
| Předmět: |
Statistics and Probability
education.field_of_study Observational error Proportional hazards model Applied Mathematics General Mathematics Maximum likelihood Population Estimator Agricultural and Biological Sciences (miscellaneous) Relative risk Cohort Covariate Statistics Econometrics Statistics Probability and Uncertainty General Agricultural and Biological Sciences education Mathematics |
| Zdroj: | Biometrika. 86:221-226 |
| ISSN: | 1464-3510 0006-3444 |
| DOI: | 10.1093/biomet/86.1.221 |
| Popis: | We investigate the question of whether or not estimates of relative risk from matched case-control studies well represent the population from which they were drawn. We derive the formula for the asymptotic maximum partial likelihood estimators from nested case-control studies when the Cox proportional hazards model is misspecified and compare these to the corresponding full cohort values under various types of model misspecification, such as covariate omission, mismodelling available measurements and covariates measured with error. We found that lack of covariate information, as in covariate omission and measurement error, cannot per se result in differences in case-control and cohort estimates. Differences can only occur when the covariates used in the presumed model are mismodelled and we find that the magnitude of the misspecification must be unreasonably large in order to produce differences of practical importance. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|