Examining the utility of nonlinear machine learning approaches versus linear regression for predicting body image outcomes: The U.S. Body Project I.
Body image
Deep neural networks
Machine learning
Random forest
Tripartite model
Journal
Body image
ISSN: 1873-6807
Titre abrégé: Body Image
Pays: Netherlands
ID NLM: 101222431
Informations de publication
Date de publication:
Jun 2022
Jun 2022
Historique:
received:
16
12
2020
revised:
14
12
2021
accepted:
26
01
2022
pubmed:
2
3
2022
medline:
7
6
2022
entrez:
1
3
2022
Statut:
ppublish
Résumé
Most body image studies assess only linear relations between predictors and outcome variables, relying on techniques such as multiple Linear Regression. These predictor variables are often validated multi-item measures that aggregate individual items into a single scale. The advent of machine learning has made it possible to apply Nonlinear Regression algorithms-such as Random Forest and Deep Neural Networks-to identify potentially complex linear and nonlinear connections between a multitude of predictors (e.g., all individual items from a scale) and outcome (output) variables. Using a national dataset, we tested the extent to which these techniques allowed us to explain a greater share of the variance in body-image outcomes (adjusted R
Identifiants
pubmed: 35228102
pii: S1740-1445(22)00012-2
doi: 10.1016/j.bodyim.2022.01.013
pii:
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
32-45Informations de copyright
Copyright © 2022 Elsevier Ltd. All rights reserved.