Small-Variance Priors Can Prevent Detecting Important Misspecifications in Bayesian Confirmatory Factor Analysis

Terrence D. Jorgensen; Mauricio Garnier-Villarreal; Sunthud Pornprasermanit; Jaehoon Lee

doi:10.1007/978-3-030-01310-3_23

Small-Variance Priors Can Prevent Detecting Important Misspecifications in Bayesian Confirmatory Factor Analysis

Terrence D. Jorgensen^*, Mauricio Garnier-Villarreal, Sunthud Pornprasermanit, Jaehoon Lee

^*Corresponding author for this work

Research output: Chapter in Book / Report / Conference proceeding › Conference contribution › Academic › peer-review

Abstract

We simulated Bayesian CFA models to investigate the power of PPP to detect model misspecification by manipulating sample size, strongly and weakly informative priors for nontarget parameters, degree of misspecification, and whether data were generated and analyzed as normal or ordinal. Rejection rates indicate that PPP lacks power to reject an inappropriate model unless priors are unrealistically restrictive (essentially equivalent to fixing nontarget parameters to zero) and both sample size and misspecification are quite large. We suggest researchers evaluate global fit without priors for nontarget parameters, then search for neglected parameters if PPP indicates poor fit.

Original language	English
Title of host publication	Quantitative Psychology - 83rd Annual Meeting of the Psychometric Society, 2018
Editors	Rianne Janssen, Steven Culpepper, Marie Wiberg, Dylan Molenaar, Jorge González
Publisher	Springer New York LLC
Pages	255-263
Number of pages	9
ISBN (Print)	9783030013097
DOIs	https://doi.org/10.1007/978-3-030-01310-3_23
Publication status	Published - 1 Jan 2019
Externally published	Yes
Event	83rd Annual meeting of the Psychometric Society, 2018 - New York, United States Duration: 9 Jul 2018 → 13 Jul 2018

Publication series

Name	Springer Proceedings in Mathematics and Statistics
Volume	265
ISSN (Print)	2194-1009
ISSN (Electronic)	2194-1017

Conference

Conference	83rd Annual meeting of the Psychometric Society, 2018
Country/Territory	United States
City	New York
Period	9/07/18 → 13/07/18

Keywords

Bayesian inference
Confirmatory factor analysis
Model evaluation
Model modification
Structural equation modeling

Access to Document

10.1007/978-3-030-01310-3_23

Persistent URL (handle)

Persistent link

Cite this

Jorgensen, T. D., Garnier-Villarreal, M., Pornprasermanit, S., & Lee, J. (2019). Small-Variance Priors Can Prevent Detecting Important Misspecifications in Bayesian Confirmatory Factor Analysis. In R. Janssen, S. Culpepper, M. Wiberg, D. Molenaar, & J. González (Eds.), Quantitative Psychology - 83rd Annual Meeting of the Psychometric Society, 2018 (pp. 255-263). (Springer Proceedings in Mathematics and Statistics; Vol. 265). Springer New York LLC. https://doi.org/10.1007/978-3-030-01310-3_23

Jorgensen, Terrence D. ; Garnier-Villarreal, Mauricio ; Pornprasermanit, Sunthud et al. / Small-Variance Priors Can Prevent Detecting Important Misspecifications in Bayesian Confirmatory Factor Analysis. Quantitative Psychology - 83rd Annual Meeting of the Psychometric Society, 2018. editor / Rianne Janssen ; Steven Culpepper ; Marie Wiberg ; Dylan Molenaar ; Jorge González. Springer New York LLC, 2019. pp. 255-263 (Springer Proceedings in Mathematics and Statistics).

@inproceedings{af99f86f79dd4e86bbde4f71d301f356,

title = "Small-Variance Priors Can Prevent Detecting Important Misspecifications in Bayesian Confirmatory Factor Analysis",

abstract = "We simulated Bayesian CFA models to investigate the power of PPP to detect model misspecification by manipulating sample size, strongly and weakly informative priors for nontarget parameters, degree of misspecification, and whether data were generated and analyzed as normal or ordinal. Rejection rates indicate that PPP lacks power to reject an inappropriate model unless priors are unrealistically restrictive (essentially equivalent to fixing nontarget parameters to zero) and both sample size and misspecification are quite large. We suggest researchers evaluate global fit without priors for nontarget parameters, then search for neglected parameters if PPP indicates poor fit.",

keywords = "Bayesian inference, Confirmatory factor analysis, Model evaluation, Model modification, Structural equation modeling",

author = "Jorgensen, {Terrence D.} and Mauricio Garnier-Villarreal and Sunthud Pornprasermanit and Jaehoon Lee",

year = "2019",

month = jan,

day = "1",

doi = "10.1007/978-3-030-01310-3_23",

language = "English",

isbn = "9783030013097",

series = "Springer Proceedings in Mathematics and Statistics",

publisher = "Springer New York LLC",

pages = "255--263",

editor = "Rianne Janssen and Steven Culpepper and Marie Wiberg and Dylan Molenaar and Jorge Gonz{\'a}lez",

booktitle = "Quantitative Psychology - 83rd Annual Meeting of the Psychometric Society, 2018",

note = "83rd Annual meeting of the Psychometric Society, 2018 ; Conference date: 09-07-2018 Through 13-07-2018",

}

Jorgensen, TD, Garnier-Villarreal, M, Pornprasermanit, S & Lee, J 2019, Small-Variance Priors Can Prevent Detecting Important Misspecifications in Bayesian Confirmatory Factor Analysis. in R Janssen, S Culpepper, M Wiberg, D Molenaar & J González (eds), Quantitative Psychology - 83rd Annual Meeting of the Psychometric Society, 2018. Springer Proceedings in Mathematics and Statistics, vol. 265, Springer New York LLC, pp. 255-263, 83rd Annual meeting of the Psychometric Society, 2018, New York, United States, 9/07/18. https://doi.org/10.1007/978-3-030-01310-3_23

Small-Variance Priors Can Prevent Detecting Important Misspecifications in Bayesian Confirmatory Factor Analysis. / Jorgensen, Terrence D.; Garnier-Villarreal, Mauricio; Pornprasermanit, Sunthud et al.
Quantitative Psychology - 83rd Annual Meeting of the Psychometric Society, 2018. ed. / Rianne Janssen; Steven Culpepper; Marie Wiberg; Dylan Molenaar; Jorge González. Springer New York LLC, 2019. p. 255-263 (Springer Proceedings in Mathematics and Statistics; Vol. 265).

Research output: Chapter in Book / Report / Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Small-Variance Priors Can Prevent Detecting Important Misspecifications in Bayesian Confirmatory Factor Analysis

AU - Jorgensen, Terrence D.

AU - Garnier-Villarreal, Mauricio

AU - Pornprasermanit, Sunthud

AU - Lee, Jaehoon

PY - 2019/1/1

Y1 - 2019/1/1

N2 - We simulated Bayesian CFA models to investigate the power of PPP to detect model misspecification by manipulating sample size, strongly and weakly informative priors for nontarget parameters, degree of misspecification, and whether data were generated and analyzed as normal or ordinal. Rejection rates indicate that PPP lacks power to reject an inappropriate model unless priors are unrealistically restrictive (essentially equivalent to fixing nontarget parameters to zero) and both sample size and misspecification are quite large. We suggest researchers evaluate global fit without priors for nontarget parameters, then search for neglected parameters if PPP indicates poor fit.

AB - We simulated Bayesian CFA models to investigate the power of PPP to detect model misspecification by manipulating sample size, strongly and weakly informative priors for nontarget parameters, degree of misspecification, and whether data were generated and analyzed as normal or ordinal. Rejection rates indicate that PPP lacks power to reject an inappropriate model unless priors are unrealistically restrictive (essentially equivalent to fixing nontarget parameters to zero) and both sample size and misspecification are quite large. We suggest researchers evaluate global fit without priors for nontarget parameters, then search for neglected parameters if PPP indicates poor fit.

KW - Bayesian inference

KW - Confirmatory factor analysis

KW - Model evaluation

KW - Model modification

KW - Structural equation modeling

UR - http://www.scopus.com/inward/record.url?scp=85066068138&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85066068138&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-01310-3_23

DO - 10.1007/978-3-030-01310-3_23

M3 - Conference contribution

AN - SCOPUS:85066068138

SN - 9783030013097

T3 - Springer Proceedings in Mathematics and Statistics

SP - 255

EP - 263

BT - Quantitative Psychology - 83rd Annual Meeting of the Psychometric Society, 2018

A2 - Janssen, Rianne

A2 - Culpepper, Steven

A2 - Wiberg, Marie

A2 - Molenaar, Dylan

A2 - González, Jorge

PB - Springer New York LLC

T2 - 83rd Annual meeting of the Psychometric Society, 2018

Y2 - 9 July 2018 through 13 July 2018

ER -

Jorgensen TD, Garnier-Villarreal M, Pornprasermanit S, Lee J. Small-Variance Priors Can Prevent Detecting Important Misspecifications in Bayesian Confirmatory Factor Analysis. In Janssen R, Culpepper S, Wiberg M, Molenaar D, González J, editors, Quantitative Psychology - 83rd Annual Meeting of the Psychometric Society, 2018. Springer New York LLC. 2019. p. 255-263. (Springer Proceedings in Mathematics and Statistics). doi: 10.1007/978-3-030-01310-3_23

Small-Variance Priors Can Prevent Detecting Important Misspecifications in Bayesian Confirmatory Factor Analysis

Abstract

Publication series

Conference

Keywords

Access to Document

Persistent URL (handle)

Other files and links

Fingerprint

Cite this