Skip to main content
PMC home page
Occupational and Environmental Medicine logoLink to Occupational and Environmental Medicine
. 1998 Apr;55(4):272–277. doi: 10.1136/oem.55.4.272

Prevalence odds ratio or prevalence ratio in the analysis of cross sectional data: what is to be done?

M L Thompson, J E Myers, D Kriebel
PMCID: PMC1757577  PMID: 9624282

Abstract

OBJECTIVES: To review the appropriateness of the prevalence odds ratio (POR) and the prevalence ratio (PR) as effect measures in the analysis of cross sectional data and to evaluate different models for the multivariate estimation of the PR. METHODS: A system of linear differential equations corresponding to a dynamic model of a cohort with a chronic disease was developed. At any point in time, a cross sectional analysis of the people then in the cohort provided a prevalence based measure of the effect of exposure on disease. This formed the basis for exploring the relations between the POR, the PR, and the incidence rate ratio (IRR). Examples illustrate relations for various IRRs, prevalences, and differential exodus rates. Multivariate point and interval estimation of the PR by logistic regression is illustrated and compared with the results from proportional hazards regression (PH) and generalised linear modelling (GLM). RESULTS: The POR is difficult to interpret without making restrictive assumptions and the POR and PR may lead to different conclusions with regard to confounding and effect modification. The PR is always conservative relative to the IRR and, if PR > 1, the POR is always > PR. In a fixed cohort and with an adverse exposure, the POR is always > or = IRR, but in a dynamic cohort with sufficient underlying follow up the POR may overestimate or underestimate the IRR, depending on the duration of follow up. Logistic regression models provide point and interval estimates of the PR (and POR) but may be intractable in the presence of many covariates. Proportional hazards and generalised linear models provide statistical methods directed specifically at the PR, but the interval estimation in the case of PH is conservative and the GLM procedure may require constrained estimation. CONCLUSIONS: The PR is conservative, consistent, and interpretable relative to the IRR and should be used in preference to the POR. Multivariate estimation of the PR should be executed by means of generalised linear models or, conservatively, by proportional hazards regression.

 

Full Text

The Full Text of this article is available as a PDF (132.0 KB).

Selected References

These references are in PubMed. This may not be the complete list of references from this article.

  1. Alho J. M. On prevalence, incidence, and duration in general stable populations. Biometrics. 1992 Jun;48(2):587–592. [PubMed] [Google Scholar]
  2. Axelson O., Fredriksson M., Ekberg K. Use of the prevalence ratio v the prevalence odds ratio as a measure of risk in cross sectional studies. Occup Environ Med. 1994 Aug;51(8):574–574. doi: 10.1136/oem.51.8.574. [DOI] [PMC free article] [PubMed] [Google Scholar]
  3. Axelson O., Fredriksson M., Ekberg K. Use of the prevalence ratio v the prevalence odds ratio in view of confounding in cross sectional studies. Occup Environ Med. 1995 Jul;52(7):494–494. doi: 10.1136/oem.52.7.494. [DOI] [PMC free article] [PubMed] [Google Scholar]
  4. Axelson O. Some recent developments in occupational epidemiology. Scand J Work Environ Health. 1994;20(Spec No):9–18. [PubMed] [Google Scholar]
  5. Breslow N. Covariance analysis of censored survival data. Biometrics. 1974 Mar;30(1):89–99. [PubMed] [Google Scholar]
  6. Eisen E. A. Healthy worker effect in morbidity studies. Med Lav. 1995 Mar-Apr;86(2):125–138. [PubMed] [Google Scholar]
  7. Greenland S. Interpretation and choice of effect measures in epidemiologic analyses. Am J Epidemiol. 1987 May;125(5):761–768. doi: 10.1093/oxfordjournals.aje.a114593. [DOI] [PubMed] [Google Scholar]
  8. Hughes K. Odds ratios in cross-sectional studies. Int J Epidemiol. 1995 Apr;24(2):463-4, 468. doi: 10.1093/ije/24.2.463. [DOI] [PubMed] [Google Scholar]
  9. Lee J., Chia K. S. Estimation of prevalence rate ratios for cross sectional data: an example in occupational epidemiology. Br J Ind Med. 1993 Sep;50(9):861–862. doi: 10.1136/oem.50.9.861. [DOI] [PMC free article] [PubMed] [Google Scholar]
  10. Lee J., Chia K. S. Prevalence odds ratio v prevalence ratio--a response. Occup Environ Med. 1995 Nov;52(11):781–782. doi: 10.1136/oem.52.11.781-a. [DOI] [PMC free article] [PubMed] [Google Scholar]
  11. Lee J., Chia K. S. Use of the prevalence ratio v the prevalence odds ratio as a measure of risk in cross sectional studies. Occup Environ Med. 1994 Dec;51(12):841–841. doi: 10.1136/oem.51.12.841. [DOI] [PMC free article] [PubMed] [Google Scholar]
  12. Lee J. Odds ratio or relative risk for cross-sectional data? Int J Epidemiol. 1994 Feb;23(1):201–203. doi: 10.1093/ije/23.1.201. [DOI] [PubMed] [Google Scholar]
  13. Nurminen M. On the epidemiologic notion of confounding and confounder identification. Scand J Work Environ Health. 1997 Feb;23(1):64–68. [PubMed] [Google Scholar]
  14. Nurminen M. To use or not to use the odds ratio in epidemiologic analyses? Eur J Epidemiol. 1995 Aug;11(4):365–371. doi: 10.1007/BF01721219. [DOI] [PubMed] [Google Scholar]
  15. Osborn J., Cattaruzza M. S. Odds ratio and relative risk for cross-sectional data. Int J Epidemiol. 1995 Apr;24(2):464–465. doi: 10.1093/ije/24.2.464. [DOI] [PubMed] [Google Scholar]
  16. Steineck G., Ahlbom A. A definition of bias founded on the concept of the study base. Epidemiology. 1992 Nov;3(6):477–482. doi: 10.1097/00001648-199211000-00003. [DOI] [PubMed] [Google Scholar]
  17. Strömberg U. Prevalence odds ratio v prevalence ratio--some further comments. Occup Environ Med. 1995 Feb;52(2):143–143. doi: 10.1136/oem.52.2.143. [DOI] [PMC free article] [PubMed] [Google Scholar]
  18. Strömberg U. Prevalence odds ratio v prevalence ratio. Occup Environ Med. 1994 Feb;51(2):143–144. doi: 10.1136/oem.51.2.143. [DOI] [PMC free article] [PubMed] [Google Scholar]
  19. Zocchetti C., Consonni D., Bertazzi P. A. Estimation of prevalence rate ratios from cross-sectional data. Int J Epidemiol. 1995 Oct;24(5):1064–1067. doi: 10.1093/ije/24.5.1064. [DOI] [PubMed] [Google Scholar]
  20. Zocchetti C., Consonni D., Bertazzi P. A. Relationship between prevalence rate ratios and odds ratios in cross-sectional studies. Int J Epidemiol. 1997 Feb;26(1):220–223. doi: 10.1093/ije/26.1.220. [DOI] [PubMed] [Google Scholar]

Articles from Occupational and Environmental Medicine are provided here courtesy of BMJ Publishing Group

RESOURCES