Robustness of autoencoders for establishing psychometric properties based on small sample sizes: results from a Monte Carlo simulation study and a sports fan curiosity study.

Autoencoder Construct validity Dimension reduction Factor analysis Principal component analysis Sample size

Journal

PeerJ. Computer science
ISSN: 2376-5992
Titre abrégé: PeerJ Comput Sci
Pays: United States
ID NLM: 101660598

Informations de publication

Date de publication:
2022
Historique:
received: 15 07 2021
accepted: 21 10 2021
entrez: 2 5 2022
pubmed: 3 5 2022
medline: 3 5 2022
Statut: epublish

Résumé

The principal component analysis (PCA) is known as a multivariate statistical model for reducing dimensions into a representation of principal components. Thus, the PCA is commonly adopted for establishing psychometric properties, A Monte Carlo simulation was conducted, varying the levels of non-normality, sample sizes, and levels of communality. The performances of autoencoders and a PCA were compared using the mean square error, mean absolute value, and Euclidian distance. The feasibility of autoencoders with small sample sizes was examined. With extreme flexibility in decoding representation using linear and non-linear mapping, this study demonstrated that the autoencoder can robustly reduce dimensions, and hence was effective in building the construct validity with a sample size as small as 100. The autoencoders could obtain a smaller mean square error and small Euclidian distance between original dataset and predictions for a small non-normal dataset. Hence, when behavioral scientists attempt to explore the construct validity of a newly designed questionnaire, an autoencoder could also be considered an alternative to a PCA.

Sections du résumé

Background UNASSIGNED
The principal component analysis (PCA) is known as a multivariate statistical model for reducing dimensions into a representation of principal components. Thus, the PCA is commonly adopted for establishing psychometric properties,
Methodology UNASSIGNED
A Monte Carlo simulation was conducted, varying the levels of non-normality, sample sizes, and levels of communality. The performances of autoencoders and a PCA were compared using the mean square error, mean absolute value, and Euclidian distance. The feasibility of autoencoders with small sample sizes was examined.
Conclusions UNASSIGNED
With extreme flexibility in decoding representation using linear and non-linear mapping, this study demonstrated that the autoencoder can robustly reduce dimensions, and hence was effective in building the construct validity with a sample size as small as 100. The autoencoders could obtain a smaller mean square error and small Euclidian distance between original dataset and predictions for a small non-normal dataset. Hence, when behavioral scientists attempt to explore the construct validity of a newly designed questionnaire, an autoencoder could also be considered an alternative to a PCA.

Identifiants

pubmed: 35494838
doi: 10.7717/peerj-cs.782
pii: cs-782
pmc: PMC9044230
doi:

Types de publication

Journal Article

Langues

eng

Pagination

e782

Informations de copyright

©2022 Lin et al.

Déclaration de conflit d'intérêts

The authors declare there are no competing interests.

Références

Support Care Cancer. 2017 Oct;25(10):3059-3066
pubmed: 28455545
Multivariate Behav Res. 2001 Oct 1;36(4):611-37
pubmed: 26822184
Am J Drug Alcohol Abuse. 1986;12(1-2):131-46
pubmed: 3788895
Behav Res Methods. 2012 Dec;44(4):1239-43
pubmed: 22351614
Psychol Bull. 1959 Mar;56(2):81-105
pubmed: 13634291
Bioinformatics. 2001 Sep;17(9):763-74
pubmed: 11590094
Psychol Bull. 1955 Jul;52(4):281-302
pubmed: 13245896
Biol Cybern. 1988;59(4-5):291-4
pubmed: 3196773

Auteurs

Yen-Kuang Lin (YK)

Graduate Institute of Athletics and Coaching Science, National Taiwan Sport University, Taoyuan, Taiwan.

Chen-Yin Lee (CY)

Department of Applied Foreign Languages, MingDao University, Changhua, Taiwan.

Chen-Yueh Chen (CY)

Department of Leisure and Recreation Industry Management, National Taiwan Sport University, Taoyuan, Taiwan.

Classifications MeSH