Improving Measurement Precision of Test Batteries Using Multidimensional Item Response Models

Wen Chung Wang, Po Hsi Chen, Ying Yao Cheng

Research output: Contribution to journalReview article

78 Citations (Scopus)

Abstract

A conventional way to analyze item responses in multiple tests is to apply unidimensional item response models separately, one test at a time. This unidimensional approach, which ignores the correlations between latent traits, yields imprecise measures when tests are short. To resolve this problem, one can use multidimensional item response models that use correlations between latent traits to improve measurement precision of individual latent traits. The improvements are demonstrated using 2 empirical examples. It appears that the multidimensional approach improves measurement precision substantially, especially when tests are short and the number of tests is large. To achieve the same measurement precision, the multidimensional approach needs less than half of the comparable items required for the unidimensional approach.

Original languageEnglish
Pages (from-to)116-136
Number of pages21
JournalPsychological Methods
Volume9
Issue number1
DOIs
Publication statusPublished - 2004 Mar 1

ASJC Scopus subject areas

  • Psychology (miscellaneous)

Cite this

Improving Measurement Precision of Test Batteries Using Multidimensional Item Response Models. / Wang, Wen Chung; Chen, Po Hsi; Cheng, Ying Yao.

In: Psychological Methods, Vol. 9, No. 1, 01.03.2004, p. 116-136.

Research output: Contribution to journalReview article

@article{f95f7e09bfb4446593dbc85052054b21,
title = "Improving Measurement Precision of Test Batteries Using Multidimensional Item Response Models",
abstract = "A conventional way to analyze item responses in multiple tests is to apply unidimensional item response models separately, one test at a time. This unidimensional approach, which ignores the correlations between latent traits, yields imprecise measures when tests are short. To resolve this problem, one can use multidimensional item response models that use correlations between latent traits to improve measurement precision of individual latent traits. The improvements are demonstrated using 2 empirical examples. It appears that the multidimensional approach improves measurement precision substantially, especially when tests are short and the number of tests is large. To achieve the same measurement precision, the multidimensional approach needs less than half of the comparable items required for the unidimensional approach.",
author = "Wang, {Wen Chung} and Chen, {Po Hsi} and Cheng, {Ying Yao}",
year = "2004",
month = "3",
day = "1",
doi = "10.1037/1082-989X.9.1.116",
language = "English",
volume = "9",
pages = "116--136",
journal = "Psychological Methods",
issn = "1082-989X",
publisher = "American Psychological Association Inc.",
number = "1",

}

TY - JOUR

T1 - Improving Measurement Precision of Test Batteries Using Multidimensional Item Response Models

AU - Wang, Wen Chung

AU - Chen, Po Hsi

AU - Cheng, Ying Yao

PY - 2004/3/1

Y1 - 2004/3/1

N2 - A conventional way to analyze item responses in multiple tests is to apply unidimensional item response models separately, one test at a time. This unidimensional approach, which ignores the correlations between latent traits, yields imprecise measures when tests are short. To resolve this problem, one can use multidimensional item response models that use correlations between latent traits to improve measurement precision of individual latent traits. The improvements are demonstrated using 2 empirical examples. It appears that the multidimensional approach improves measurement precision substantially, especially when tests are short and the number of tests is large. To achieve the same measurement precision, the multidimensional approach needs less than half of the comparable items required for the unidimensional approach.

AB - A conventional way to analyze item responses in multiple tests is to apply unidimensional item response models separately, one test at a time. This unidimensional approach, which ignores the correlations between latent traits, yields imprecise measures when tests are short. To resolve this problem, one can use multidimensional item response models that use correlations between latent traits to improve measurement precision of individual latent traits. The improvements are demonstrated using 2 empirical examples. It appears that the multidimensional approach improves measurement precision substantially, especially when tests are short and the number of tests is large. To achieve the same measurement precision, the multidimensional approach needs less than half of the comparable items required for the unidimensional approach.

UR - http://www.scopus.com/inward/record.url?scp=1942443121&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=1942443121&partnerID=8YFLogxK

U2 - 10.1037/1082-989X.9.1.116

DO - 10.1037/1082-989X.9.1.116

M3 - Review article

C2 - 15053722

AN - SCOPUS:1942443121

VL - 9

SP - 116

EP - 136

JO - Psychological Methods

JF - Psychological Methods

SN - 1082-989X

IS - 1

ER -