Applied prevalence ratio estimation with different regression models: An example from a cross-national study on substance use research

Albert Espelt, Marc Marí-Dell’olmo, Eva Penelo, Marina Bosque-Prous

Research output: Contribution to journalArticleResearchpeer-review

48 Citations (Scopus)

Abstract

© 2017, Edita Socidrogalcohol. All rights reserved. Objective: To examine the differences between Prevalence Ratio (PR) and Odds Ratio (OR) in a cross-sectional study and to provide tools to calculate PR using two statistical packages widely used in substance use research (STATA and R). Methods: We used cross-sectional data from 41,263 participants of 16 European countries participating in the Survey on Health, Ageing and Retirement in Europe (SHARE). The dependent variable, hazardous drinking, was calculated using the Alcohol Use Disorders Identification Test – Consumption (AUDIT-C). The main independent variable was gender. Other variables used were: age, educational level and country of residence. PR of hazardous drinking in men with relation to women was estimated using Mantel-Haenszel method, log-binomial regression models and poisson regression models with robust variance. These estimations were compared to the OR calculated using logistic regression models. Results: Prevalence of hazardous drinkers varied among countries. Generally, men have higher prevalence of hazardous drinking than women [PR=1.43 (1.38-1.47)]. Estimated PR was identical independently of the method and the statistical package used. However, OR overestimated PR, depending on the prevalence of hazardous drinking in the country. Conclusions: In cross-sectional studies, where comparisons between countries with differences in the prevalence of the disease or condition are made, it is advisable to use PR instead of OR.
Original languageEnglish
Pages (from-to)105-112
JournalAdicciones
Volume29
DOIs
Publication statusPublished - 1 Jan 2017

Keywords

  • Cross-sectional studies
  • Log-binomial regression
  • Odds ratio
  • Poisson regression
  • Prevalence ratio

Fingerprint Dive into the research topics of 'Applied prevalence ratio estimation with different regression models: An example from a cross-national study on substance use research'. Together they form a unique fingerprint.

  • Cite this