Assessing unidimensionality of polytomous data

Ratna Nandakumar, Feng Yu, Hsin-Hung Li, William Stout

Research output: Contribution to journalArticle

30 Citations (Scopus)

Abstract

This study investigated the performance of Poly-DIMTEST (PD) to assess unidimensionality of test data produced by polytomous items. Two types of polytomous data were considered: (1) tests in which all items had the same number of response categories, and (2) tests in which items had a mixed number of response categories. Test length, sample size, and the type of correlation matrix (used in factor analysis for selecting AT1 subset items) were varied in Type I error analyses. For the power study, the correlation between θs and the item-θ loadings were also varied. The results showed that PD was able to confirm unidimensionality for unidimensional simulated test data, with the average observed level of significance slightly below the nominal level. PD was also highly effective in detecting lack of unidimensionality in various two-dimensional tests. As expected, power increased as the sample size and test length increased, and the correlation between the θs decreased. The results also demonstrated that use of Pearson correlations to select AT1 items led to equally good or better performance than using polychoric correlations; therefore Pearson correlations are recommended for future use.

Original languageEnglish
Pages (from-to)99-115
Number of pages17
JournalApplied Psychological Measurement
Volume22
Issue number2
DOIs
Publication statusPublished - 1998 Jan 1

Fingerprint

Sample Size
Statistical Factor Analysis
performance
factor analysis
lack

All Science Journal Classification (ASJC) codes

  • Social Sciences (miscellaneous)
  • Psychology (miscellaneous)

Cite this

Nandakumar, Ratna ; Yu, Feng ; Li, Hsin-Hung ; Stout, William. / Assessing unidimensionality of polytomous data. In: Applied Psychological Measurement. 1998 ; Vol. 22, No. 2. pp. 99-115.
@article{94b2d14bbe5248aa9acd548aac675e54,
title = "Assessing unidimensionality of polytomous data",
abstract = "This study investigated the performance of Poly-DIMTEST (PD) to assess unidimensionality of test data produced by polytomous items. Two types of polytomous data were considered: (1) tests in which all items had the same number of response categories, and (2) tests in which items had a mixed number of response categories. Test length, sample size, and the type of correlation matrix (used in factor analysis for selecting AT1 subset items) were varied in Type I error analyses. For the power study, the correlation between θs and the item-θ loadings were also varied. The results showed that PD was able to confirm unidimensionality for unidimensional simulated test data, with the average observed level of significance slightly below the nominal level. PD was also highly effective in detecting lack of unidimensionality in various two-dimensional tests. As expected, power increased as the sample size and test length increased, and the correlation between the θs decreased. The results also demonstrated that use of Pearson correlations to select AT1 items led to equally good or better performance than using polychoric correlations; therefore Pearson correlations are recommended for future use.",
author = "Ratna Nandakumar and Feng Yu and Hsin-Hung Li and William Stout",
year = "1998",
month = "1",
day = "1",
doi = "10.1177/01466216980222001",
language = "English",
volume = "22",
pages = "99--115",
journal = "Applied Psychological Measurement",
issn = "0146-6216",
publisher = "SAGE Publications Inc.",
number = "2",

}

Assessing unidimensionality of polytomous data. / Nandakumar, Ratna; Yu, Feng; Li, Hsin-Hung; Stout, William.

In: Applied Psychological Measurement, Vol. 22, No. 2, 01.01.1998, p. 99-115.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Assessing unidimensionality of polytomous data

AU - Nandakumar, Ratna

AU - Yu, Feng

AU - Li, Hsin-Hung

AU - Stout, William

PY - 1998/1/1

Y1 - 1998/1/1

N2 - This study investigated the performance of Poly-DIMTEST (PD) to assess unidimensionality of test data produced by polytomous items. Two types of polytomous data were considered: (1) tests in which all items had the same number of response categories, and (2) tests in which items had a mixed number of response categories. Test length, sample size, and the type of correlation matrix (used in factor analysis for selecting AT1 subset items) were varied in Type I error analyses. For the power study, the correlation between θs and the item-θ loadings were also varied. The results showed that PD was able to confirm unidimensionality for unidimensional simulated test data, with the average observed level of significance slightly below the nominal level. PD was also highly effective in detecting lack of unidimensionality in various two-dimensional tests. As expected, power increased as the sample size and test length increased, and the correlation between the θs decreased. The results also demonstrated that use of Pearson correlations to select AT1 items led to equally good or better performance than using polychoric correlations; therefore Pearson correlations are recommended for future use.

AB - This study investigated the performance of Poly-DIMTEST (PD) to assess unidimensionality of test data produced by polytomous items. Two types of polytomous data were considered: (1) tests in which all items had the same number of response categories, and (2) tests in which items had a mixed number of response categories. Test length, sample size, and the type of correlation matrix (used in factor analysis for selecting AT1 subset items) were varied in Type I error analyses. For the power study, the correlation between θs and the item-θ loadings were also varied. The results showed that PD was able to confirm unidimensionality for unidimensional simulated test data, with the average observed level of significance slightly below the nominal level. PD was also highly effective in detecting lack of unidimensionality in various two-dimensional tests. As expected, power increased as the sample size and test length increased, and the correlation between the θs decreased. The results also demonstrated that use of Pearson correlations to select AT1 items led to equally good or better performance than using polychoric correlations; therefore Pearson correlations are recommended for future use.

UR - http://www.scopus.com/inward/record.url?scp=0032392513&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032392513&partnerID=8YFLogxK

U2 - 10.1177/01466216980222001

DO - 10.1177/01466216980222001

M3 - Article

VL - 22

SP - 99

EP - 115

JO - Applied Psychological Measurement

JF - Applied Psychological Measurement

SN - 0146-6216

IS - 2

ER -