Display options
Cite
Greenland S. Small-sample bias and corrections for conditional maximum-likelihood odds-ratio estimators. Biostatistics. 2000;1(1):113-22doi: 10.1093/biostatistics/1.1.113.
Greenland, S. (2000). Small-sample bias and corrections for conditional maximum-likelihood odds-ratio estimators. Biostatistics (Oxford, England), 1(1), 113-22. https://doi.org/10.1093/biostatistics/1.1.113
Greenland, S. "Small-sample bias and corrections for conditional maximum-likelihood odds-ratio estimators." Biostatistics (Oxford, England) vol. 1,1 (2000): 113-22. doi: https://doi.org/10.1093/biostatistics/1.1.113
Greenland S. Small-sample bias and corrections for conditional maximum-likelihood odds-ratio estimators. Biostatistics. 2000 Mar;1(1):113-22. doi: 10.1093/biostatistics/1.1.113. PMID: 12933529.
Copy Download .nbib Format: NLM
Share it on

Biostatistics. 2000 Mar;1(1):113-22. doi: 10.1093/biostatistics/1.1.113.

Small-sample bias and corrections for conditional maximum-likelihood odds-ratio estimators.

Biostatistics (Oxford, England)

S Greenland

Affiliations

  1. Department of Epidemiology, UCLA School of Public Health, Los Angeles, CA 90095-1772, USA.

PMID: 12933529 DOI: 10.1093/biostatistics/1.1.113

Abstract

A number of small-sample corrections have been proposed for the conditional maximum-likelihood estimator of the odds ratio for matched pairs with a dichotomous exposure. I here contrast the rationale and performance of several corrections, specifically those that generalize easily to multiple conditional logistic regression. These corrections or Bayesian analyses with informative priors may serve as diagnostics for small-sample problems. Points are illustrated with a small exact performance comparison and with an example from a study of electrical wiring and childhood leukemia. The former comparison suggests that small-sample bias may be more prevalent than commonly realized.

Publication Types