Joint Maximum Likelihood Estimation for Diagnostic Classification Models

Chia Yi Chiu, Hans Friedrich Koehn, Yi Zheng, Robert Henson

Research output: Contribution to journalArticle

Abstract

Joint maximum likelihood estimation (JMLE) is developed for diagnostic classification models (DCMs). JMLE has been barely used in Psychometrics because JMLE parameter estimators typically lack statistical consistency. The JMLE procedure presented here resolves the consistency issue by incorporating an external, statistically consistent estimator of examinees’ proficiency class membership into the joint likelihood function, which subsequently allows for the construction of item parameter estimators that also have the consistency property. Consistency of the JMLE parameter estimators is established within the framework of general DCMs: The JMLE parameter estimators are derived for the Loglinear Cognitive Diagnosis Model (LCDM). Two consistency theorems are proven for the LCDM. Using the framework of general DCMs makes the results and proofs also applicable to DCMs that can be expressed as submodels of the LCDM. Simulation studies are reported for evaluating the performance of JMLE when used with tests of varying length and different numbers of attributes. As a practical application, JMLE is also used with “real world” educational data collected with a language proficiency test.

Original languageEnglish (US)
Pages (from-to)1069-1092
Number of pages24
JournalPsychometrika
Volume81
Issue number4
DOIs
StatePublished - Dec 1 2016

Fingerprint

Maximum likelihood estimation
Maximum Likelihood Estimation
Diagnostics
Joints
Estimator
Model
Likelihood Functions
Language Tests
Psychometrics
Consistent Estimator
Likelihood Function
Resolve
Attribute
Simulation Study
Theorem

Keywords

  • cognitive diagnosis
  • joint maximum likelihood estimation
  • nonparametric classification
  • statistical consistency

ASJC Scopus subject areas

  • Psychology(all)
  • Applied Mathematics

Cite this

Joint Maximum Likelihood Estimation for Diagnostic Classification Models. / Chiu, Chia Yi; Koehn, Hans Friedrich; Zheng, Yi; Henson, Robert.

In: Psychometrika, Vol. 81, No. 4, 01.12.2016, p. 1069-1092.

Research output: Contribution to journalArticle

Chiu, Chia Yi ; Koehn, Hans Friedrich ; Zheng, Yi ; Henson, Robert. / Joint Maximum Likelihood Estimation for Diagnostic Classification Models. In: Psychometrika. 2016 ; Vol. 81, No. 4. pp. 1069-1092.
@article{02acf3e2064c401789d4a917ca026c4d,
title = "Joint Maximum Likelihood Estimation for Diagnostic Classification Models",
abstract = "Joint maximum likelihood estimation (JMLE) is developed for diagnostic classification models (DCMs). JMLE has been barely used in Psychometrics because JMLE parameter estimators typically lack statistical consistency. The JMLE procedure presented here resolves the consistency issue by incorporating an external, statistically consistent estimator of examinees’ proficiency class membership into the joint likelihood function, which subsequently allows for the construction of item parameter estimators that also have the consistency property. Consistency of the JMLE parameter estimators is established within the framework of general DCMs: The JMLE parameter estimators are derived for the Loglinear Cognitive Diagnosis Model (LCDM). Two consistency theorems are proven for the LCDM. Using the framework of general DCMs makes the results and proofs also applicable to DCMs that can be expressed as submodels of the LCDM. Simulation studies are reported for evaluating the performance of JMLE when used with tests of varying length and different numbers of attributes. As a practical application, JMLE is also used with “real world” educational data collected with a language proficiency test.",
keywords = "cognitive diagnosis, joint maximum likelihood estimation, nonparametric classification, statistical consistency",
author = "Chiu, {Chia Yi} and Koehn, {Hans Friedrich} and Yi Zheng and Robert Henson",
year = "2016",
month = "12",
day = "1",
doi = "10.1007/s11336-016-9534-9",
language = "English (US)",
volume = "81",
pages = "1069--1092",
journal = "Psychometrika",
issn = "0033-3123",
publisher = "Springer New York",
number = "4",

}

TY - JOUR

T1 - Joint Maximum Likelihood Estimation for Diagnostic Classification Models

AU - Chiu, Chia Yi

AU - Koehn, Hans Friedrich

AU - Zheng, Yi

AU - Henson, Robert

PY - 2016/12/1

Y1 - 2016/12/1

N2 - Joint maximum likelihood estimation (JMLE) is developed for diagnostic classification models (DCMs). JMLE has been barely used in Psychometrics because JMLE parameter estimators typically lack statistical consistency. The JMLE procedure presented here resolves the consistency issue by incorporating an external, statistically consistent estimator of examinees’ proficiency class membership into the joint likelihood function, which subsequently allows for the construction of item parameter estimators that also have the consistency property. Consistency of the JMLE parameter estimators is established within the framework of general DCMs: The JMLE parameter estimators are derived for the Loglinear Cognitive Diagnosis Model (LCDM). Two consistency theorems are proven for the LCDM. Using the framework of general DCMs makes the results and proofs also applicable to DCMs that can be expressed as submodels of the LCDM. Simulation studies are reported for evaluating the performance of JMLE when used with tests of varying length and different numbers of attributes. As a practical application, JMLE is also used with “real world” educational data collected with a language proficiency test.

AB - Joint maximum likelihood estimation (JMLE) is developed for diagnostic classification models (DCMs). JMLE has been barely used in Psychometrics because JMLE parameter estimators typically lack statistical consistency. The JMLE procedure presented here resolves the consistency issue by incorporating an external, statistically consistent estimator of examinees’ proficiency class membership into the joint likelihood function, which subsequently allows for the construction of item parameter estimators that also have the consistency property. Consistency of the JMLE parameter estimators is established within the framework of general DCMs: The JMLE parameter estimators are derived for the Loglinear Cognitive Diagnosis Model (LCDM). Two consistency theorems are proven for the LCDM. Using the framework of general DCMs makes the results and proofs also applicable to DCMs that can be expressed as submodels of the LCDM. Simulation studies are reported for evaluating the performance of JMLE when used with tests of varying length and different numbers of attributes. As a practical application, JMLE is also used with “real world” educational data collected with a language proficiency test.

KW - cognitive diagnosis

KW - joint maximum likelihood estimation

KW - nonparametric classification

KW - statistical consistency

UR - http://www.scopus.com/inward/record.url?scp=84991049099&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84991049099&partnerID=8YFLogxK

U2 - 10.1007/s11336-016-9534-9

DO - 10.1007/s11336-016-9534-9

M3 - Article

C2 - 27734298

AN - SCOPUS:84991049099

VL - 81

SP - 1069

EP - 1092

JO - Psychometrika

JF - Psychometrika

SN - 0033-3123

IS - 4

ER -