General mixture item response models with different item response structures

Exposition with an application to Likert scales

J. Tijmstra, Maria Bolsinova, Minjeong Jeon

Research output: Contribution to journalArticleScientificpeer-review

17 Downloads (Pure)

Abstract

This article proposes a general mixture item response theory (IRT) framework that allows for classes of persons to differ with respect to the type of processes underlying the item responses. Through the use of mixture models, nonnested IRT models with different structures can be estimated for different classes, and class membership can be estimated for each person in the sample. If researchers are able to provide competing measurement models, this mixture IRT framework may help them deal with some violations of measurement invariance. To illustrate this approach, we consider a two-class mixture model, where a person's responses to Likert-scale items containing a neutral middle category are either modeled using a generalized partial credit model, or through an IRTree model. In the first model, the middle category ("neither agree nor disagree") is taken to be qualitatively similar to the other categories, and is taken to provide information about the person's endorsement. In the second model, the middle category is taken to be qualitatively different and to reflect a nonresponse choice, which is modeled using an additional latent variable that captures a person's willingness to respond. The mixture model is studied using simulation studies and is applied to an empirical example.
Original languageEnglish
Pages (from-to)2325–2344
JournalBehavior Research Methods
Volume50
Issue number6
DOIs
Publication statusPublished - 2018

Fingerprint

Exposition
Person
Mixture Model
Item Response Theory
Simulation
Credit
Willingness
Violations
Invariance

Keywords

  • ABILITY
  • CATEGORY
  • DISTRIBUTIONS
  • EXPLANATION
  • EXTENSION
  • General mixture item response models
  • IRT MODELS
  • IRTree models
  • Item response theory
  • LATENT CLASSES
  • Likert scales
  • MEASUREMENT INVARIANCE
  • Measurement invariance
  • Mixture modeling
  • Response styles
  • STYLES
  • VALIDITY

Cite this

@article{c3ec4c127d3c4be9a462d29e6b8e0f3b,
title = "General mixture item response models with different item response structures: Exposition with an application to Likert scales",
abstract = "This article proposes a general mixture item response theory (IRT) framework that allows for classes of persons to differ with respect to the type of processes underlying the item responses. Through the use of mixture models, nonnested IRT models with different structures can be estimated for different classes, and class membership can be estimated for each person in the sample. If researchers are able to provide competing measurement models, this mixture IRT framework may help them deal with some violations of measurement invariance. To illustrate this approach, we consider a two-class mixture model, where a person's responses to Likert-scale items containing a neutral middle category are either modeled using a generalized partial credit model, or through an IRTree model. In the first model, the middle category ({"}neither agree nor disagree{"}) is taken to be qualitatively similar to the other categories, and is taken to provide information about the person's endorsement. In the second model, the middle category is taken to be qualitatively different and to reflect a nonresponse choice, which is modeled using an additional latent variable that captures a person's willingness to respond. The mixture model is studied using simulation studies and is applied to an empirical example.",
keywords = "ABILITY, CATEGORY, DISTRIBUTIONS, EXPLANATION, EXTENSION, General mixture item response models, IRT MODELS, IRTree models, Item response theory, LATENT CLASSES, Likert scales, MEASUREMENT INVARIANCE, Measurement invariance, Mixture modeling, Response styles, STYLES, VALIDITY",
author = "J. Tijmstra and Maria Bolsinova and Minjeong Jeon",
year = "2018",
doi = "10.3758/s13428-017-0997-0",
language = "English",
volume = "50",
pages = "2325–2344",
journal = "Behavior Research Methods",
issn = "1554-351X",
publisher = "Springer",
number = "6",

}

General mixture item response models with different item response structures : Exposition with an application to Likert scales. / Tijmstra, J.; Bolsinova, Maria; Jeon, Minjeong.

In: Behavior Research Methods, Vol. 50, No. 6, 2018, p. 2325–2344.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - General mixture item response models with different item response structures

T2 - Exposition with an application to Likert scales

AU - Tijmstra, J.

AU - Bolsinova, Maria

AU - Jeon, Minjeong

PY - 2018

Y1 - 2018

N2 - This article proposes a general mixture item response theory (IRT) framework that allows for classes of persons to differ with respect to the type of processes underlying the item responses. Through the use of mixture models, nonnested IRT models with different structures can be estimated for different classes, and class membership can be estimated for each person in the sample. If researchers are able to provide competing measurement models, this mixture IRT framework may help them deal with some violations of measurement invariance. To illustrate this approach, we consider a two-class mixture model, where a person's responses to Likert-scale items containing a neutral middle category are either modeled using a generalized partial credit model, or through an IRTree model. In the first model, the middle category ("neither agree nor disagree") is taken to be qualitatively similar to the other categories, and is taken to provide information about the person's endorsement. In the second model, the middle category is taken to be qualitatively different and to reflect a nonresponse choice, which is modeled using an additional latent variable that captures a person's willingness to respond. The mixture model is studied using simulation studies and is applied to an empirical example.

AB - This article proposes a general mixture item response theory (IRT) framework that allows for classes of persons to differ with respect to the type of processes underlying the item responses. Through the use of mixture models, nonnested IRT models with different structures can be estimated for different classes, and class membership can be estimated for each person in the sample. If researchers are able to provide competing measurement models, this mixture IRT framework may help them deal with some violations of measurement invariance. To illustrate this approach, we consider a two-class mixture model, where a person's responses to Likert-scale items containing a neutral middle category are either modeled using a generalized partial credit model, or through an IRTree model. In the first model, the middle category ("neither agree nor disagree") is taken to be qualitatively similar to the other categories, and is taken to provide information about the person's endorsement. In the second model, the middle category is taken to be qualitatively different and to reflect a nonresponse choice, which is modeled using an additional latent variable that captures a person's willingness to respond. The mixture model is studied using simulation studies and is applied to an empirical example.

KW - ABILITY

KW - CATEGORY

KW - DISTRIBUTIONS

KW - EXPLANATION

KW - EXTENSION

KW - General mixture item response models

KW - IRT MODELS

KW - IRTree models

KW - Item response theory

KW - LATENT CLASSES

KW - Likert scales

KW - MEASUREMENT INVARIANCE

KW - Measurement invariance

KW - Mixture modeling

KW - Response styles

KW - STYLES

KW - VALIDITY

U2 - 10.3758/s13428-017-0997-0

DO - 10.3758/s13428-017-0997-0

M3 - Article

VL - 50

SP - 2325

EP - 2344

JO - Behavior Research Methods

JF - Behavior Research Methods

SN - 1554-351X

IS - 6

ER -