Abstract
We have studied Miettinen's multivariate confounder score method of controlling confounding in case-control studies both theoretically and by simulation. The main conclusion to be drawn from out results is that the method will in many practical situations seriously exaggerate the statistical significance achieved, and its use is not to be recommended.
Full text
PDF
Selected References
These references are in PubMed. This may not be the complete list of references from this article.
- Breslow N., Powers W. Are there two logistic regressions for retrospective studies? Biometrics. 1978 Mar;34(1):100–105. [PubMed] [Google Scholar]
- Holford T. R., White C., Kelsey J. L. Multivariate analysis for matched case-control studies. Am J Epidemiol. 1978 Mar;107(3):245–256. doi: 10.1093/oxfordjournals.aje.a112531. [DOI] [PubMed] [Google Scholar]
- MANTEL N., HAENSZEL W. Statistical aspects of the analysis of data from retrospective studies of disease. J Natl Cancer Inst. 1959 Apr;22(4):719–748. [PubMed] [Google Scholar]
- Miettinen O. S. Stratification by a multivariate confounder score. Am J Epidemiol. 1976 Dec;104(6):609–620. doi: 10.1093/oxfordjournals.aje.a112339. [DOI] [PubMed] [Google Scholar]