Finite mixture models in neighbourhoods-to-health research: A systematic review

P. Lekkas; I. Stankov; Mark Daniel; Catherine Paquet

doi:10.1016/j.healthplace.2019.05.018

Finite mixture models in neighbourhoods-to-health research: A systematic review

P. Lekkas
, I. Stankov
, Mark Daniel
, Catherine Paquet

Health Research Institute

Research output: Contribution to journal › Literature review › peer-review

10 Citations (Scopus)

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.

Original language	English
Article number	102140
Pages (from-to)	1-24
Number of pages	24
Journal	Health and Place
Volume	59
DOIs	https://doi.org/10.1016/j.healthplace.2019.05.018
Publication status	Published - Sept 2019

Access to Document

10.1016/j.healthplace.2019.05.018

Cite this

@article{88d62d67e8804ed9accff13f431eb07d,

title = "Finite mixture models in neighbourhoods-to-health research: A systematic review",

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.",

keywords = "Ecological, Finite mixture modeling, Latent class analysis, Latent profile analysis, Neigborhood effects, Systematic review",

author = "P. Lekkas and I. Stankov and Mark Daniel and Catherine Paquet",

note = "Funding Information: Mr Peter Lekkas was supported by: a Research Training Scheme (formerly the Australian Postgraduate Award), Department of Education and Training, Australian Government ; a University of South Australia {\textquoteleft}Top-up{\textquoteright} Scholarship ; and a {\textquoteleft}Top-up{\textquoteright} Scholarship from the School of Health Sciences, University of South Australia facilitated through the then position of the Research Chair, Social Epidemiology. Dr Catherine Paquet was funded by a National Health and Medical Research Council (Australia) Program Grant ( \#0631947 ). Adjunct Prof. Mark Daniel formerly held the position of Research Chair, Social Epidemiology, University of South Australia. The authors thank Dr Julie Collins (University of South Australia) for her thoughts and comments. Publisher Copyright: {\textcopyright} 2019",

year = "2019",

month = sep,

doi = "10.1016/j.healthplace.2019.05.018",

language = "English",

volume = "59",

pages = "1--24",

journal = "Health and Place",

issn = "1353-8292",

publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Finite mixture models in neighbourhoods-to-health research

T2 - A systematic review

AU - Lekkas, P.

AU - Stankov, I.

AU - Daniel, Mark

AU - Paquet, Catherine

N1 - Funding Information: Mr Peter Lekkas was supported by: a Research Training Scheme (formerly the Australian Postgraduate Award), Department of Education and Training, Australian Government ; a University of South Australia ‘Top-up’ Scholarship ; and a ‘Top-up’ Scholarship from the School of Health Sciences, University of South Australia facilitated through the then position of the Research Chair, Social Epidemiology. Dr Catherine Paquet was funded by a National Health and Medical Research Council (Australia) Program Grant ( #0631947 ). Adjunct Prof. Mark Daniel formerly held the position of Research Chair, Social Epidemiology, University of South Australia. The authors thank Dr Julie Collins (University of South Australia) for her thoughts and comments. Publisher Copyright: © 2019

PY - 2019/9

Y1 - 2019/9

N2 - 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.

AB - 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.

KW - Ecological

KW - Finite mixture modeling

KW - Latent class analysis

KW - Latent profile analysis

KW - Neigborhood effects

KW - Systematic review

UR - https://www.scopus.com/pages/publications/85069805949

U2 - 10.1016/j.healthplace.2019.05.018

DO - 10.1016/j.healthplace.2019.05.018

M3 - Literature review

C2 - 31374380

AN - SCOPUS:85069805949

SN - 1353-8292

VL - 59

SP - 1

EP - 24

JO - Health and Place

JF - Health and Place

M1 - 102140

ER -

Finite mixture models in neighbourhoods-to-health research: A systematic review

Abstract

Access to Document

Other files and links

Fingerprint

Cite this