Marginalized Maximum Likelihood Estimation for the 1PL-AG IRT Model

Ryoungsun Park; Keenan A. Pituch; Jiseon Kim; Barbara G. Dodd; Hyewon Chung

doi:10.1177/0146621615574694

Marginalized Maximum Likelihood Estimation for the 1PL-AG IRT Model

Ryoungsun Park, Keenan A. Pituch, Jiseon Kim, Barbara G. Dodd, Hyewon Chung

Research output: Contribution to journal › Article › peer-review

2 Scopus citations

Abstract

Marginal maximum likelihood estimation based on the expectation–maximization algorithm (MML/EM) is developed for the one-parameter logistic model with ability-based guessing (1PL-AG) item response theory (IRT) model. The use of the MML/EM estimator is cross-validated with estimates from NLMIXED procedure (PROC NLMIXED) in Statistical Analysis System. Numerical data are provided for comparisons of results from MML/EM and PROC NLMIXED.

Original language	English (US)
Pages (from-to)	448-464
Number of pages	17
Journal	Applied Psychological Measurement
Volume	39
Issue number	6
DOIs	https://doi.org/10.1177/0146621615574694
State	Published - Sep 8 2015
Externally published	Yes

Keywords

1PL-AG
EM
IRT
MML
estimator

ASJC Scopus subject areas

Social Sciences (miscellaneous)
Psychology (miscellaneous)

Access to Document

10.1177/0146621615574694

Cite this

@article{8d42c75c5e6c466589b35b3087479997,

title = "Marginalized Maximum Likelihood Estimation for the 1PL-AG IRT Model",

abstract = "Marginal maximum likelihood estimation based on the expectation–maximization algorithm (MML/EM) is developed for the one-parameter logistic model with ability-based guessing (1PL-AG) item response theory (IRT) model. The use of the MML/EM estimator is cross-validated with estimates from NLMIXED procedure (PROC NLMIXED) in Statistical Analysis System. Numerical data are provided for comparisons of results from MML/EM and PROC NLMIXED.",

keywords = "1PL-AG, EM, IRT, MML, estimator",

author = "Ryoungsun Park and Pituch, {Keenan A.} and Jiseon Kim and Dodd, {Barbara G.} and Hyewon Chung",

note = "Publisher Copyright: {\textcopyright} 2015, {\textcopyright} The Author(s) 2015.",

year = "2015",

month = sep,

day = "8",

doi = "10.1177/0146621615574694",

language = "English (US)",

volume = "39",

pages = "448--464",

journal = "Applied Psychological Measurement",

issn = "0146-6216",

publisher = "SAGE Publications Inc.",

number = "6",

}

TY - JOUR

T1 - Marginalized Maximum Likelihood Estimation for the 1PL-AG IRT Model

AU - Park, Ryoungsun

AU - Pituch, Keenan A.

AU - Kim, Jiseon

AU - Dodd, Barbara G.

AU - Chung, Hyewon

PY - 2015/9/8

Y1 - 2015/9/8

N2 - Marginal maximum likelihood estimation based on the expectation–maximization algorithm (MML/EM) is developed for the one-parameter logistic model with ability-based guessing (1PL-AG) item response theory (IRT) model. The use of the MML/EM estimator is cross-validated with estimates from NLMIXED procedure (PROC NLMIXED) in Statistical Analysis System. Numerical data are provided for comparisons of results from MML/EM and PROC NLMIXED.

AB - Marginal maximum likelihood estimation based on the expectation–maximization algorithm (MML/EM) is developed for the one-parameter logistic model with ability-based guessing (1PL-AG) item response theory (IRT) model. The use of the MML/EM estimator is cross-validated with estimates from NLMIXED procedure (PROC NLMIXED) in Statistical Analysis System. Numerical data are provided for comparisons of results from MML/EM and PROC NLMIXED.

KW - 1PL-AG

KW - EM

KW - IRT

KW - MML

KW - estimator

UR - http://www.scopus.com/inward/record.url?scp=84938697091&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84938697091&partnerID=8YFLogxK

U2 - 10.1177/0146621615574694

DO - 10.1177/0146621615574694

M3 - Article

AN - SCOPUS:84938697091

SN - 0146-6216

VL - 39

SP - 448

EP - 464

JO - Applied Psychological Measurement

JF - Applied Psychological Measurement

IS - 6

ER -

Marginalized Maximum Likelihood Estimation for the 1PL-AG IRT Model

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this