Bayesian Versus Maximum Likelihood Estimation of Multitrait–Multimethod Confirmatory Factor Models

Jonathan Lee Helm, Laura Castro-Schilo, Zita Oravecz

Research output: Research - peer-reviewArticle

  • 1 Citations

Abstract

This article compares maximum likelihood and Bayesian estimation of the correlated trait–correlated method (CT–CM) confirmatory factor model for multitrait–multimethod (MTMM) data. In particular, Bayesian estimation with minimally informative prior distributions—that is, prior distributions that prescribe equal probability across the known mathematical range of a parameter—are investigated as a source of information to aid convergence. Results from a simulation study indicate that Bayesian estimation with minimally informative priors produces admissible solutions more often maximum likelihood estimation (100.00% for Bayesian estimation, 49.82% for maximum likelihood). Extra convergence does not come at the cost of parameter accuracy; Bayesian parameter estimates showed comparable bias and better efficiency compared to maximum likelihood estimates. The results are echoed via 2 empirical examples. Hence, Bayesian estimation with minimally informative priors outperforms enables admissible solutions of the CT–CM model for MTMM data.

LanguageEnglish (US)
Pages17-30
Number of pages14
JournalStructural Equation Modeling
Volume24
Issue number1
DOIs
StatePublished - Jan 2 2017

Fingerprint

Factor Models
Bayesian Estimation
Maximum Likelihood Estimation
Maximum likelihood estimation
Bayesian estimation
Multi-method
Maximum likelihood
Prior distribution
Maximum Likelihood Estimate
Maximum Likelihood
Simulation Study
Estimate
Range of data
Model
Simulation study
Sources of information
source of information
efficiency
simulation
trend

Keywords

  • Bayesian estimation
  • CT–CM
  • minimally informative priors
  • MTMM

ASJC Scopus subject areas

  • Decision Sciences(all)
  • Modeling and Simulation
  • Sociology and Political Science
  • Economics, Econometrics and Finance(all)

Cite this

Bayesian Versus Maximum Likelihood Estimation of Multitrait–Multimethod Confirmatory Factor Models. / Helm, Jonathan Lee; Castro-Schilo, Laura; Oravecz, Zita.

In: Structural Equation Modeling, Vol. 24, No. 1, 02.01.2017, p. 17-30.

Research output: Research - peer-reviewArticle

@article{235abb8ed89640c9a12a0d9b562fd332,
title = "Bayesian Versus Maximum Likelihood Estimation of Multitrait–Multimethod Confirmatory Factor Models",
abstract = "This article compares maximum likelihood and Bayesian estimation of the correlated trait–correlated method (CT–CM) confirmatory factor model for multitrait–multimethod (MTMM) data. In particular, Bayesian estimation with minimally informative prior distributions—that is, prior distributions that prescribe equal probability across the known mathematical range of a parameter—are investigated as a source of information to aid convergence. Results from a simulation study indicate that Bayesian estimation with minimally informative priors produces admissible solutions more often maximum likelihood estimation (100.00% for Bayesian estimation, 49.82% for maximum likelihood). Extra convergence does not come at the cost of parameter accuracy; Bayesian parameter estimates showed comparable bias and better efficiency compared to maximum likelihood estimates. The results are echoed via 2 empirical examples. Hence, Bayesian estimation with minimally informative priors outperforms enables admissible solutions of the CT–CM model for MTMM data.",
keywords = "Bayesian estimation, CT–CM, minimally informative priors, MTMM",
author = "Helm, {Jonathan Lee} and Laura Castro-Schilo and Zita Oravecz",
year = "2017",
month = "1",
doi = "10.1080/10705511.2016.1236261",
volume = "24",
pages = "17--30",
journal = "Structural Equation Modeling",
issn = "1070-5511",
publisher = "Psychology Press Ltd",
number = "1",

}

TY - JOUR

T1 - Bayesian Versus Maximum Likelihood Estimation of Multitrait–Multimethod Confirmatory Factor Models

AU - Helm,Jonathan Lee

AU - Castro-Schilo,Laura

AU - Oravecz,Zita

PY - 2017/1/2

Y1 - 2017/1/2

N2 - This article compares maximum likelihood and Bayesian estimation of the correlated trait–correlated method (CT–CM) confirmatory factor model for multitrait–multimethod (MTMM) data. In particular, Bayesian estimation with minimally informative prior distributions—that is, prior distributions that prescribe equal probability across the known mathematical range of a parameter—are investigated as a source of information to aid convergence. Results from a simulation study indicate that Bayesian estimation with minimally informative priors produces admissible solutions more often maximum likelihood estimation (100.00% for Bayesian estimation, 49.82% for maximum likelihood). Extra convergence does not come at the cost of parameter accuracy; Bayesian parameter estimates showed comparable bias and better efficiency compared to maximum likelihood estimates. The results are echoed via 2 empirical examples. Hence, Bayesian estimation with minimally informative priors outperforms enables admissible solutions of the CT–CM model for MTMM data.

AB - This article compares maximum likelihood and Bayesian estimation of the correlated trait–correlated method (CT–CM) confirmatory factor model for multitrait–multimethod (MTMM) data. In particular, Bayesian estimation with minimally informative prior distributions—that is, prior distributions that prescribe equal probability across the known mathematical range of a parameter—are investigated as a source of information to aid convergence. Results from a simulation study indicate that Bayesian estimation with minimally informative priors produces admissible solutions more often maximum likelihood estimation (100.00% for Bayesian estimation, 49.82% for maximum likelihood). Extra convergence does not come at the cost of parameter accuracy; Bayesian parameter estimates showed comparable bias and better efficiency compared to maximum likelihood estimates. The results are echoed via 2 empirical examples. Hence, Bayesian estimation with minimally informative priors outperforms enables admissible solutions of the CT–CM model for MTMM data.

KW - Bayesian estimation

KW - CT–CM

KW - minimally informative priors

KW - MTMM

UR - http://www.scopus.com/inward/record.url?scp=84991503392&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84991503392&partnerID=8YFLogxK

U2 - 10.1080/10705511.2016.1236261

DO - 10.1080/10705511.2016.1236261

M3 - Article

VL - 24

SP - 17

EP - 30

JO - Structural Equation Modeling

T2 - Structural Equation Modeling

JF - Structural Equation Modeling

SN - 1070-5511

IS - 1

ER -