Fitting the Reduced RUM with Mplus: A Tutorial

Chia Yi Chiu, Hans Friedrich Koehn, Huey Min Wu

Research output: Contribution to journalArticle

Abstract

The Reduced Reparameterized Unified Model (Reduced RUM) is a diagnostic classification model for educational assessment that has received considerable attention among psychometricians. However, the computational options for researchers and practitioners who wish to use the Reduced RUM in their work, but do not feel comfortable writing their own code, are still rather limited. One option is to use a commercial software package that offers an implementation of the expectation maximization (EM) algorithm for fitting (constrained) latent class models like Latent GOLD or Mplus. But using a latent class analysis routine as a vehicle for fitting the Reduced RUM requires that it be re-expressed as a logit model, with constraints imposed on the parameters of the logistic function. This tutorial demonstrates how to implement marginal maximum likelihood estimation using the EM algorithm in Mplus for fitting the Reduced RUM.

Original languageEnglish (US)
Pages (from-to)331-351
Number of pages21
JournalInternational Journal of Testing
Volume16
Issue number4
DOIs
StatePublished - Oct 1 2016

Fingerprint

Educational Measurement
Expectation-maximization Algorithm
Software
Logistic Models
Research Personnel
Marginal Maximum Likelihood
Latent Class Analysis
Latent Class Model
Logit Model
Model
Maximum Likelihood Estimation
Software Package
Logistics
Diagnostics
Maximum likelihood estimation
Software packages
diagnostic
logistics
Demonstrate

Keywords

  • LCDM
  • MCMC
  • Mplus
  • cognitive diagnosis
  • diagnostic models
  • general cognitive
  • reduced RUM EM

ASJC Scopus subject areas

  • Social Psychology
  • Education
  • Modeling and Simulation

Cite this

Fitting the Reduced RUM with Mplus : A Tutorial. / Chiu, Chia Yi; Koehn, Hans Friedrich; Wu, Huey Min.

In: International Journal of Testing, Vol. 16, No. 4, 01.10.2016, p. 331-351.

Research output: Contribution to journalArticle

Chiu, Chia Yi ; Koehn, Hans Friedrich ; Wu, Huey Min. / Fitting the Reduced RUM with Mplus : A Tutorial. In: International Journal of Testing. 2016 ; Vol. 16, No. 4. pp. 331-351.
@article{9e8843a25a0444b3acd0c19645a89553,
title = "Fitting the Reduced RUM with Mplus: A Tutorial",
abstract = "The Reduced Reparameterized Unified Model (Reduced RUM) is a diagnostic classification model for educational assessment that has received considerable attention among psychometricians. However, the computational options for researchers and practitioners who wish to use the Reduced RUM in their work, but do not feel comfortable writing their own code, are still rather limited. One option is to use a commercial software package that offers an implementation of the expectation maximization (EM) algorithm for fitting (constrained) latent class models like Latent GOLD or Mplus. But using a latent class analysis routine as a vehicle for fitting the Reduced RUM requires that it be re-expressed as a logit model, with constraints imposed on the parameters of the logistic function. This tutorial demonstrates how to implement marginal maximum likelihood estimation using the EM algorithm in Mplus for fitting the Reduced RUM.",
keywords = "LCDM, MCMC, Mplus, cognitive diagnosis, diagnostic models, general cognitive, reduced RUM EM",
author = "Chiu, {Chia Yi} and Koehn, {Hans Friedrich} and Wu, {Huey Min}",
year = "2016",
month = "10",
day = "1",
doi = "10.1080/15305058.2016.1148038",
language = "English (US)",
volume = "16",
pages = "331--351",
journal = "International Journal of Testing",
issn = "1530-5058",
publisher = "Routledge",
number = "4",

}

TY - JOUR

T1 - Fitting the Reduced RUM with Mplus

T2 - A Tutorial

AU - Chiu, Chia Yi

AU - Koehn, Hans Friedrich

AU - Wu, Huey Min

PY - 2016/10/1

Y1 - 2016/10/1

N2 - The Reduced Reparameterized Unified Model (Reduced RUM) is a diagnostic classification model for educational assessment that has received considerable attention among psychometricians. However, the computational options for researchers and practitioners who wish to use the Reduced RUM in their work, but do not feel comfortable writing their own code, are still rather limited. One option is to use a commercial software package that offers an implementation of the expectation maximization (EM) algorithm for fitting (constrained) latent class models like Latent GOLD or Mplus. But using a latent class analysis routine as a vehicle for fitting the Reduced RUM requires that it be re-expressed as a logit model, with constraints imposed on the parameters of the logistic function. This tutorial demonstrates how to implement marginal maximum likelihood estimation using the EM algorithm in Mplus for fitting the Reduced RUM.

AB - The Reduced Reparameterized Unified Model (Reduced RUM) is a diagnostic classification model for educational assessment that has received considerable attention among psychometricians. However, the computational options for researchers and practitioners who wish to use the Reduced RUM in their work, but do not feel comfortable writing their own code, are still rather limited. One option is to use a commercial software package that offers an implementation of the expectation maximization (EM) algorithm for fitting (constrained) latent class models like Latent GOLD or Mplus. But using a latent class analysis routine as a vehicle for fitting the Reduced RUM requires that it be re-expressed as a logit model, with constraints imposed on the parameters of the logistic function. This tutorial demonstrates how to implement marginal maximum likelihood estimation using the EM algorithm in Mplus for fitting the Reduced RUM.

KW - LCDM

KW - MCMC

KW - Mplus

KW - cognitive diagnosis

KW - diagnostic models

KW - general cognitive

KW - reduced RUM EM

UR - http://www.scopus.com/inward/record.url?scp=84964076662&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84964076662&partnerID=8YFLogxK

U2 - 10.1080/15305058.2016.1148038

DO - 10.1080/15305058.2016.1148038

M3 - Article

AN - SCOPUS:84964076662

VL - 16

SP - 331

EP - 351

JO - International Journal of Testing

JF - International Journal of Testing

SN - 1530-5058

IS - 4

ER -