A simple multilevel approach for analysing geographical inequalities in public health reports: The case of municipality differences in obesity. (July 2019)

• Record Type: Journal Article
• Authors: Merlo, Juan; Wagner, Philippe; Leckie, George
• Is Part Of: Health & place. Volume 58(2019:Jul.)
• Publication Date: 2019-07
• Subjects: Public health -- Geographical differences -- Multilevel analysis -- Discriminatory accuracy -- Obesity; Health -- Social aspects -- Periodicals; Health services accessibility -- Periodicals; Public health -- Periodicals; Political planning -- Periodicals; Social medicine -- Periodicals; Epidemiology -- Periodicals; Health Policy -- Periodicals; Health Services Accessibility -- Periodicals; Public Health -- Periodicals; Public Policy -- Periodicals; Sociology, Medical -- Periodicals; Épidémiologie -- Périodiques; Politique sanitaire -- Périodiques; Santé, Services de -- Accessibilité -- Périodiques; Health services accessibility; Health -- Social aspects; Political planning; Public health; Social medicine; Periodicals; 613
• DOI: 10.1016/j.healthplace.2019.102145
• Languages: English
• ISSNs: 1353-8292

Abstract

Abstract: The epidemiological analysis of geographical inequalities in individual outcomes is a fundamental theme in public health research. However, many traditional studies focus on analysing area differences in averages outcomes, disregarding individual variation around such averages. In doing so, these studies may produce misleading information and lead researchers to draw incorrect conclusions. Analysing individual and municipality differences in body mass index (BMI) and overweight/obesity status, we apply an analytical approach based on the multilevel analysis of individual heterogeneity and discriminatory accuracy (MAIHDA). This analytical approach may be viewed as a reorganization of existing multilevel modelling concepts in order to provide a systematic approach to simultaneously considering both differences between area averages and individual heterogeneity around those averages. In doing so, MAIHDA provides an improved approach to the quantification and understanding of geographical inequalities as compared with traditional approaches. Highlights: Analysis of geographical inequalities is a fundamental theme in public health. Traditional studies focus on area differences in average health outcomes. Ignoring individual variation within areas may produce misleading information. We show how multilevel modelling can solve this problem via a study of obesity. We use non-technical language to explain the methodology to a broad audience.