Bayesian Estimation for Item Factor Analysis Models with Sparse Categorical Indicators

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Psychometric models for item-level data are broadly useful in psychology. A recurring issue for estimating item factor analysis (IFA) models is low-item endorsement (item sparseness), due to limited sample sizes or extreme items such as rare symptoms or behaviors. In this paper, I demonstrate that under conditions characterized by sparseness, currently available estimation methods, including maximum likelihood (ML), are likely to fail to converge or lead to extreme estimates and low empirical power. Bayesian estimation incorporating prior information is a promising alternative to ML estimation for IFA models with item sparseness. In this article, I use a simulation study to demonstrate that Bayesian estimation incorporating general prior information improves parameter estimate stability, overall variability in estimates, and power for IFA models with sparse, categorical indicators. Importantly, the priors proposed here can be generally applied to many research contexts in psychology, and they do not impact results compared to ML when indicators are not sparse. I then apply this method to examine the relationship between suicide ideation and insomnia in a sample of first-year college students. This provides an important alternative for researchers who may need to model items with sparse endorsement.

Original languageEnglish (US)
Pages (from-to)593-615
Number of pages23
JournalMultivariate Behavioral Research
Volume52
Issue number5
DOIs
StatePublished - Sep 3 2017

Fingerprint

Bayesian Estimation
Factor Analysis
Categorical
Statistical Factor Analysis
Psychology
Prior Information
Sleep Initiation and Maintenance Disorders
Psychometrics
Extremes
Sample Size
Suicide
Research Personnel
Model
Students
Stability Estimates
Alternatives
Maximum Likelihood Method
Maximum Likelihood Estimation
Estimate
Demonstrate

Keywords

  • Bayesian estimation
  • item factor analysis
  • sparse categorical indicators

ASJC Scopus subject areas

  • Statistics and Probability
  • Experimental and Cognitive Psychology
  • Arts and Humanities (miscellaneous)

Cite this

Bayesian Estimation for Item Factor Analysis Models with Sparse Categorical Indicators. / Bainter, Sierra.

In: Multivariate Behavioral Research, Vol. 52, No. 5, 03.09.2017, p. 593-615.

Research output: Contribution to journalArticle

@article{8a4516f50af7481dbba9f18e9379d8ff,
title = "Bayesian Estimation for Item Factor Analysis Models with Sparse Categorical Indicators",
abstract = "Psychometric models for item-level data are broadly useful in psychology. A recurring issue for estimating item factor analysis (IFA) models is low-item endorsement (item sparseness), due to limited sample sizes or extreme items such as rare symptoms or behaviors. In this paper, I demonstrate that under conditions characterized by sparseness, currently available estimation methods, including maximum likelihood (ML), are likely to fail to converge or lead to extreme estimates and low empirical power. Bayesian estimation incorporating prior information is a promising alternative to ML estimation for IFA models with item sparseness. In this article, I use a simulation study to demonstrate that Bayesian estimation incorporating general prior information improves parameter estimate stability, overall variability in estimates, and power for IFA models with sparse, categorical indicators. Importantly, the priors proposed here can be generally applied to many research contexts in psychology, and they do not impact results compared to ML when indicators are not sparse. I then apply this method to examine the relationship between suicide ideation and insomnia in a sample of first-year college students. This provides an important alternative for researchers who may need to model items with sparse endorsement.",
keywords = "Bayesian estimation, item factor analysis, sparse categorical indicators",
author = "Sierra Bainter",
year = "2017",
month = "9",
day = "3",
doi = "10.1080/00273171.2017.1342203",
language = "English (US)",
volume = "52",
pages = "593--615",
journal = "Multivariate Behavioral Research",
issn = "0027-3171",
publisher = "Psychology Press Ltd",
number = "5",

}

TY - JOUR

T1 - Bayesian Estimation for Item Factor Analysis Models with Sparse Categorical Indicators

AU - Bainter, Sierra

PY - 2017/9/3

Y1 - 2017/9/3

N2 - Psychometric models for item-level data are broadly useful in psychology. A recurring issue for estimating item factor analysis (IFA) models is low-item endorsement (item sparseness), due to limited sample sizes or extreme items such as rare symptoms or behaviors. In this paper, I demonstrate that under conditions characterized by sparseness, currently available estimation methods, including maximum likelihood (ML), are likely to fail to converge or lead to extreme estimates and low empirical power. Bayesian estimation incorporating prior information is a promising alternative to ML estimation for IFA models with item sparseness. In this article, I use a simulation study to demonstrate that Bayesian estimation incorporating general prior information improves parameter estimate stability, overall variability in estimates, and power for IFA models with sparse, categorical indicators. Importantly, the priors proposed here can be generally applied to many research contexts in psychology, and they do not impact results compared to ML when indicators are not sparse. I then apply this method to examine the relationship between suicide ideation and insomnia in a sample of first-year college students. This provides an important alternative for researchers who may need to model items with sparse endorsement.

AB - Psychometric models for item-level data are broadly useful in psychology. A recurring issue for estimating item factor analysis (IFA) models is low-item endorsement (item sparseness), due to limited sample sizes or extreme items such as rare symptoms or behaviors. In this paper, I demonstrate that under conditions characterized by sparseness, currently available estimation methods, including maximum likelihood (ML), are likely to fail to converge or lead to extreme estimates and low empirical power. Bayesian estimation incorporating prior information is a promising alternative to ML estimation for IFA models with item sparseness. In this article, I use a simulation study to demonstrate that Bayesian estimation incorporating general prior information improves parameter estimate stability, overall variability in estimates, and power for IFA models with sparse, categorical indicators. Importantly, the priors proposed here can be generally applied to many research contexts in psychology, and they do not impact results compared to ML when indicators are not sparse. I then apply this method to examine the relationship between suicide ideation and insomnia in a sample of first-year college students. This provides an important alternative for researchers who may need to model items with sparse endorsement.

KW - Bayesian estimation

KW - item factor analysis

KW - sparse categorical indicators

UR - http://www.scopus.com/inward/record.url?scp=85024380381&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85024380381&partnerID=8YFLogxK

U2 - 10.1080/00273171.2017.1342203

DO - 10.1080/00273171.2017.1342203

M3 - Article

C2 - 28715231

AN - SCOPUS:85024380381

VL - 52

SP - 593

EP - 615

JO - Multivariate Behavioral Research

JF - Multivariate Behavioral Research

SN - 0027-3171

IS - 5

ER -