Finite mixture models in neighbourhoods-to-health research: A systematic review. (September 2019)

• Record Type: Journal Article
• Authors: Lekkas, Peter; Stankov, Ivana; Daniel, Mark; Paquet, Catherine
• Is Part Of: Health & place. Volume 59(2019:Sep.)
• Publication Date: 2019-09
• Subjects: Ecological -- Finite mixture modeling -- Latent class analysis -- Latent profile analysis -- Neigborhood effects -- Systematic review; 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.2019.05.018
• Languages: English
• ISSNs: 1353-8292

Abstract

Abstract: A systematic review was conducted, following PRISMA guidelines, to examine the application of finite mixture models (FMMs) in the study of neighbourhoods and health. Two reviewers screened 814-studies identified through database searches and citation tracking. Data were extracted from 19-studies that met the inclusion criteria, and a risk of bias analysis undertaken. Data were synthesised narratively, with a focus on methodological issues idiosyncratic to FMMs. Motivated by a desire to account for neighbourhood heterogeneity, studies sought to identify meaningful neighbourhood-level typologies that explained the distributional nature of health outcomes. Neighbourhood-centred applications of FMMs were promising but there remains scope for advancement. Research-based recommendations are outlined to strengthen prospective neighbourhood-centred studies applying FMMs. Highlights: Neighborhoods reflect multidimensional traits, and are heterogeneous in nature. Finite mixture models (FMMs) capture neighbourhood dimensionality and heterogeneity. This review systematically surveys n19 neighbourhood-to-health studies applying FMMs. Neighbourhood-centred applications of FMMs show merit but scope for advancement. Recommendations are outlined to strengthen neighbourhood-centred FMMs.