A novel approach to latent class modelling: identifying the various types of body mass index individuals

© 2020 Royal Statistical Society Given the increasing prevalence of adult obesity, furthering understanding of the determinants of measures such as the body mass index (BMI) remains high on the policy agenda. We contribute to existing literature on modelling the BMI by proposing an extension to...

Full description

Bibliographic Details
Main Authors: Brown, S., Greene, William, Harris, Mark
Format: Journal Article
Language:English
Published: WILEY 2020
Subjects:
Online Access:http://hdl.handle.net/20.500.11937/81791
_version_ 1848764419296722944
author Brown, S.
Greene, William
Harris, Mark
author_facet Brown, S.
Greene, William
Harris, Mark
author_sort Brown, S.
building Curtin Institutional Repository
collection Online Access
description © 2020 Royal Statistical Society Given the increasing prevalence of adult obesity, furthering understanding of the determinants of measures such as the body mass index (BMI) remains high on the policy agenda. We contribute to existing literature on modelling the BMI by proposing an extension to latent class modelling, which serves to unveil a more detailed picture of the determinants of BMI. Interest here lies in latent class analysis with a regression model and predictor variables explaining class membership, a regression model and predictor variables explaining the outcome variable within BMI classes and instances where the BMI classes are naturally ordered and labelled by expected values within class. A simple and generic way of parameterizing both the class probabilities and the statistical representation of behaviours within each class is proposed, that simultaneously preserves the ranking according to class-specific expected values and yields a parsimonious representation of the class probabilities. Based on a wide range of metrics, the newly proposed approach is found to dominate the prevailing approach and, moreover, results are often quite different across the two.
first_indexed 2025-11-14T11:19:03Z
format Journal Article
id curtin-20.500.11937-81791
institution Curtin University Malaysia
institution_category Local University
language English
last_indexed 2025-11-14T11:19:03Z
publishDate 2020
publisher WILEY
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-817912021-03-15T07:01:12Z A novel approach to latent class modelling: identifying the various types of body mass index individuals Brown, S. Greene, William Harris, Mark Social Sciences Science & Technology Physical Sciences Social Sciences, Mathematical Methods Statistics & Probability Mathematical Methods In Social Sciences Mathematics Body mass index Expected values Latent class models Obesity Ordered probability models HEALTH-CARE OBESITY SELECTION STANDARD AKAIKE TRENDS IMPACT ADULT TESTS ORDER © 2020 Royal Statistical Society Given the increasing prevalence of adult obesity, furthering understanding of the determinants of measures such as the body mass index (BMI) remains high on the policy agenda. We contribute to existing literature on modelling the BMI by proposing an extension to latent class modelling, which serves to unveil a more detailed picture of the determinants of BMI. Interest here lies in latent class analysis with a regression model and predictor variables explaining class membership, a regression model and predictor variables explaining the outcome variable within BMI classes and instances where the BMI classes are naturally ordered and labelled by expected values within class. A simple and generic way of parameterizing both the class probabilities and the statistical representation of behaviours within each class is proposed, that simultaneously preserves the ranking according to class-specific expected values and yields a parsimonious representation of the class probabilities. Based on a wide range of metrics, the newly proposed approach is found to dominate the prevailing approach and, moreover, results are often quite different across the two. 2020 Journal Article http://hdl.handle.net/20.500.11937/81791 10.1111/rssa.12552 English WILEY fulltext
spellingShingle Social Sciences
Science & Technology
Physical Sciences
Social Sciences, Mathematical Methods
Statistics & Probability
Mathematical Methods In Social Sciences
Mathematics
Body mass index
Expected values
Latent class models
Obesity
Ordered probability models
HEALTH-CARE
OBESITY
SELECTION
STANDARD
AKAIKE
TRENDS
IMPACT
ADULT
TESTS
ORDER
Brown, S.
Greene, William
Harris, Mark
A novel approach to latent class modelling: identifying the various types of body mass index individuals
title A novel approach to latent class modelling: identifying the various types of body mass index individuals
title_full A novel approach to latent class modelling: identifying the various types of body mass index individuals
title_fullStr A novel approach to latent class modelling: identifying the various types of body mass index individuals
title_full_unstemmed A novel approach to latent class modelling: identifying the various types of body mass index individuals
title_short A novel approach to latent class modelling: identifying the various types of body mass index individuals
title_sort novel approach to latent class modelling: identifying the various types of body mass index individuals
topic Social Sciences
Science & Technology
Physical Sciences
Social Sciences, Mathematical Methods
Statistics & Probability
Mathematical Methods In Social Sciences
Mathematics
Body mass index
Expected values
Latent class models
Obesity
Ordered probability models
HEALTH-CARE
OBESITY
SELECTION
STANDARD
AKAIKE
TRENDS
IMPACT
ADULT
TESTS
ORDER
url http://hdl.handle.net/20.500.11937/81791