Applied Prevalence Ratio estimation with different Regression models: An example from a cross-national study on substance use research
Applied Prevalence Ratio estimation with different Regression models: An example from a cross-national study on substance use research
复制标题
DOI：
10.20882/adicciones.823
复制
发表时间：
2017-01-01
期刊：
影响因子：
3
通讯作者：
Bosque-Prous, Marina
中科院分区：
文献类型：
--
作者：
Espelt, Albert;Mari-Dell'Olmo, Marc;Bosque-Prous, Marina
目的：在横断面研究中检验患病率(PR)和优势比(OR)之间的差异，并提供使用两个在物质使用研究中广泛使用的统计软件(STATA和R)来计算PR的工具。方法：我们使用了来自16个欧洲国家的41,263名参与者的横截面数据，这些参与者参与了欧洲健康、老龄化和退休调查(SHARE)。使用酒精使用障碍识别测试消耗量(AUDIT-C)计算因变量危险饮酒。主要自变量为性别。使用的其他变量包括：年龄、教育水平和居住国。采用Mantel-Haenszel方法、对数二项回归模型和具有稳健方差的Poisson回归模型估计男性危险饮酒与女性危险饮酒的PR。将这些估计与使用Logistic回归模型计算的OR进行比较。结果：危险饮酒者的流行率因国家而异。一般来说，男性的危险饮酒患病率高于女性[PR=1.43(1.38-1.47)]。估计的PR是相同的，独立于方法和使用的统计包。然而，OR高估了PR，这取决于该国危险饮酒的流行程度。结论：在横断面研究中，在疾病患病率或病情差异的国家之间进行比较时，建议使用PR而不是OR。
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.