Within-subject exposure dependency in case-crossover studies
Article first published online: 3 OCT 2001
Copyright © 2001 John Wiley & Sons, Ltd.
Statistics in Medicine
Volume 20, Issue 20, pages 3039–3049, 30 October 2001
How to Cite
Vines, S. K. and Farrington, C. P. (2001), Within-subject exposure dependency in case-crossover studies. Statist. Med., 20: 3039–3049. doi: 10.1002/sim.960
- Issue published online: 3 OCT 2001
- Article first published online: 3 OCT 2001
- Manuscript Accepted: FEB 2001
- Manuscript Received: JUL 1999
In the case-crossover design, only cases are sampled and the hazard ratio is estimated from within-subject comparisons of exposures at the event time and in M control periods prior to the event. We consider the effect of within-subject dependence of exposures in successive time periods. We show that estimates obtained from the conditional logistic model are biased. This bias disappears if the distribution of exposures in the M+1 successive time intervals is exchangeable. In contrast, the Mantel–Haenszel estimator for the odds ratio is approximately unbiased provided that exposures are stationary. Suitable methods of analysis of case-crossover designs using maximum likelihood may be derived from cohort rather than case-control models. Copyright © 2001 John Wiley & Sons, Ltd.