Applied Prevalence Ratio estimation with different Regression models: An example from a cross-national study on substance use research

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 o...

Descripción completa

Detalles Bibliográficos
Autores: Espelt, A, Mari-Dell'Olmo, M, Penelo, E, Bosque-Prous, M
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2017
País:España
Institución:Institut d’Investigació Biomèdica Sant Pau (IIB Sant Pau)
Repositorio:r-IIB SANT PAU. Repositorio Institucional de Producción Científica del Instituto de Investigación Biomédica Sant Pau
OAI Identifier:oai:iibsantpau.fundanetsuite.com:p6716
Acceso en línea:https://iibsantpau.fundanetsuite.com/Publicaciones/ProdCientif/PublicacionFrw.aspx?id=6716
Access Level:acceso abierto
Palabra clave:Poisson regression
Log-binomial regression
Prevalence Ratio
Odds Ratio
Cross-sectional studies
id ES_aaf59ea26e80d2199c66ef7fa7b407f2
oai_identifier_str oai:iibsantpau.fundanetsuite.com:p6716
network_acronym_str ES
network_name_str España
repository_id_str
spelling Applied Prevalence Ratio estimation with different Regression models: An example from a cross-national study on substance use researchEspelt, AMari-Dell'Olmo, MPenelo, EBosque-Prous, MPoisson regressionLog-binomial regressionPrevalence RatioOdds RatioCross-sectional studiesObjective: 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.SOCIDROGALCOHOL2017info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttps://iibsantpau.fundanetsuite.com/Publicaciones/ProdCientif/PublicacionFrw.aspx?id=6716AdiccionesISSN: 02144840reponame:r-IIB SANT PAU. Repositorio Institucional de Producción Científica del Instituto de Investigación Biomédica Sant Pauinstname:Institut d’Investigació Biomèdica Sant Pau (IIB Sant Pau)Españolinfo:eu-repo/semantics/openAccessoai:iibsantpau.fundanetsuite.com:p67162026-06-14T12:41:47Z
dc.title.none.fl_str_mv Applied Prevalence Ratio estimation with different Regression models: An example from a cross-national study on substance use research
title Applied Prevalence Ratio estimation with different Regression models: An example from a cross-national study on substance use research
spellingShingle Applied Prevalence Ratio estimation with different Regression models: An example from a cross-national study on substance use research
Espelt, A
Poisson regression
Log-binomial regression
Prevalence Ratio
Odds Ratio
Cross-sectional studies
title_short Applied Prevalence Ratio estimation with different Regression models: An example from a cross-national study on substance use research
title_full Applied Prevalence Ratio estimation with different Regression models: An example from a cross-national study on substance use research
title_fullStr Applied Prevalence Ratio estimation with different Regression models: An example from a cross-national study on substance use research
title_full_unstemmed Applied Prevalence Ratio estimation with different Regression models: An example from a cross-national study on substance use research
title_sort Applied Prevalence Ratio estimation with different Regression models: An example from a cross-national study on substance use research
dc.creator.none.fl_str_mv Espelt, A
Mari-Dell'Olmo, M
Penelo, E
Bosque-Prous, M
author Espelt, A
author_facet Espelt, A
Mari-Dell'Olmo, M
Penelo, E
Bosque-Prous, M
author_role author
author2 Mari-Dell'Olmo, M
Penelo, E
Bosque-Prous, M
author2_role author
author
author
dc.subject.none.fl_str_mv Poisson regression
Log-binomial regression
Prevalence Ratio
Odds Ratio
Cross-sectional studies
topic Poisson regression
Log-binomial regression
Prevalence Ratio
Odds Ratio
Cross-sectional studies
description 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.
publishDate 2017
dc.date.none.fl_str_mv 2017
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv https://iibsantpau.fundanetsuite.com/Publicaciones/ProdCientif/PublicacionFrw.aspx?id=6716
url https://iibsantpau.fundanetsuite.com/Publicaciones/ProdCientif/PublicacionFrw.aspx?id=6716
dc.language.none.fl_str_mv Español
language_invalid_str_mv Español
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv SOCIDROGALCOHOL
publisher.none.fl_str_mv SOCIDROGALCOHOL
dc.source.none.fl_str_mv Adicciones
ISSN: 02144840
reponame:r-IIB SANT PAU. Repositorio Institucional de Producción Científica del Instituto de Investigación Biomédica Sant Pau
instname:Institut d’Investigació Biomèdica Sant Pau (IIB Sant Pau)
instname_str Institut d’Investigació Biomèdica Sant Pau (IIB Sant Pau)
reponame_str r-IIB SANT PAU. Repositorio Institucional de Producción Científica del Instituto de Investigación Biomédica Sant Pau
collection r-IIB SANT PAU. Repositorio Institucional de Producción Científica del Instituto de Investigación Biomédica Sant Pau
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869416226612051968
score 15,812429

Similares en LA Referencia