Alternatives for logistic regression in cross-sectional studies: an empirical comparison of models that directly estimate the prevalence ratio

Author(s): Barros A, Hirakata V


Background: Cross-sectional studies with binary outcomes analyzed by logistic regression are frequent in the epidemiological literature. However, the odds ratio can importantly overestimate the prevalence ratio, the measure of choice in these studies. Also, controlling for confounding is not equivalent for the two measures. In this paper we explore alternatives for modeling data of such studies with techniques that directly estimate the prevalence ratio.

Methods: We compared Cox regression with constant time at risk, Poisson regression and log-binomial regression against the standard Mantel-Haenszel estimators. Models with robust variance estimators in Cox and Poisson regressions and variance corrected by the scale parameter in Poisson regression were also evaluated.

Results: Three outcomes, from a cross-sectional study carried out in Pelotas, Brazil, with different levels of prevalence were explored: weight-for-age deficit (4%), asthma (31%) and mother in a paid job (52%). Unadjusted Cox/Poisson regression and Poisson regression with scale parameter adjusted by deviance performed worst in terms of interval estimates. Poisson regression with scale parameter adjusted by chi2 showed variable performance depending on the outcome prevalence. Cox/Poisson regression with robust variance, and log-binomial regression performed equally well when the model was correctly specified.

Conclusions: Cox or Poisson regression with robust variance and log-binomial regression provide correct estimates and are a better alternative for the analysis of cross-sectional studies with binary outcomes than logistic regression, since the prevalence ratio is more interpretable and easier to communicate to non-specialists than the odds ratio. However, precautions are needed to avoid estimation problems in specific situations.

Similar Articles

Substance-related problems in patients visiting an urban Canadian emergency department

Author(s): Brubacher JR, Mabie A, Ngo M, Abu-Laban RB, Buchanan J, et al.

Feasibility of screening and intervention for alcohol problems among young adults in the ED

Author(s): Hungerford DW, Williams JM, Furbee PM, Manley WG, Helmkamp JC, et al.

Rapid follow-up for patients after psychiatric crisis

Author(s): McCullumsmith C, Clark B, Blair C, Cropsey K, Shelton R

A review of research on the Alcohol Use Disorders Identification Test (AUDIT)

Author(s): Allen JP, Litten RZ, Fertig JB, Babor T

Evaluating the effects of a brief motivational intervention for injury drinkers in the Emergency Department

Author(s): Longabaugh R, Woolard RF, Nirenberg TD, Minugh AP, Becker B, et al.

Establishing treatment relations with alcoholics

Author(s): Chafetz ME, Blane HT, Abrams HS, Golner JH, Lacy E, et al.

The early history of ideas on brief interventions for alcohol

Author(s): McCambridge J, Cunningham JA

Individual and system influences on waiting time for substance abuse treatment

Author(s): Carr CJA, Xu J, Redko C, Lane DT, Rapp RC, et al.

Treatment barriers identified by substance abusers assessed at a centralized intake unit

Author(s): Rapp RC, Xu J, Carr CA, Lane DT, Wang J, et al.

Follow-up services after an emergency department visit for substance abuse

Author(s): Breton AR, Taira DA, Burns E, O´Leary J, Chung RS

Intervention by an alcohol health worker in an accident and emergency department

Author(s): Wright S, Moran L, Meyrick M, O’Connor R, Touquet R

Intervention attendance among Emergency Department patients with alcohol- and drug-use disorders

Author(s): Blow FC, Walton MA, Murray R, Cunningham RM, Chermack ST, et al.

Categorical Data Analysis using the SAS System

Author(s): Stokes ME, Davis CS, Koch GG