Using an Approximate Chi‐Square Statistic to Test the Number of Dimensions Underlying the Responses to a Set of Items
Journal of Educational MeasurementPublished 1 June 1996
Marc E. Gessaroli, André F. De Champlain
Citations79
SJR quartileQ1
SJR score1.09
SNIP1.58
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
Abstract
An approximate χ 2 statistic based on McDonald's (1967) nonlinear factor analytic representation of item response theory was proposed and investigated with simulated data. The results were compared with Stout's T statistic (Nandakumar & Stout, 1993; Stout, 1987). Unidimensional and two‐dimensional item response data were simulated under varying levels of sample size, test length, test reliability, and dimension dominance. The approximate χ 2 statistic had good control over Type I errors when unidimensional data were generated and displayed very good power in identifying the two‐dimensional data. The performance of the approximate χ 2 was at least as good as Stout's T statistic in all conditions and was better than Stout's T statistic with smaller sample sizes and shorter tests. Further implications regarding the potential use of nonlinear factor analysis and the approximate χ 2 in addressing current measurement issues are discussed.
Keywords
Computer ScienceDecision Sciences
Psychological BulletinTests for comparing elements of a correlation matrix.
4,421 Citations1980James H. Steiger
PsychometrikaMarginal Maximum Likelihood Estimation of Item Parameters: Application of an EM Algorithm
2,340 Citations1981R. Darrell Bock, Murray Aitkin
The Em procedure is shown to apply to general item-response models lacking simple sufficient statistics for ability, including models with more than one latent dimension, when computing procedures based on an EM algorithm are used.
Psychological BulletinChoosing a multivariate model: Noncentrality and goodness of fit.
1,379 Citations1990Roderick P. McDonald, Herbert W. Marsh
Applied Psychological MeasurementMethodology Review: Assessing Unidimensionality of Tests and ltenls
1,018 Citations1985John Hattie
PsychometrikaOn the Relationship between iTem Response Theory and Factor Analysis of Discretized Variables
698 Citations1987Yoshio Takane, Jan de Leeuw
PsychometrikaFull-Information Item Bi-Factor Analysis
600 Citations1992Robert D. Gibbons, Donald R. Hedeker
Applied Psychological MeasurementFull-Information Item Factor Analysis
532 Citations1988R. Darrell Bock, Robert D. Gibbons +1 more
PsychometrikaA Nonparametric Approach for Assessing Latent Trait Unidimensionality
506 Citations1987William Stout
Applied Psychological MeasurementThe Difficulty of Test Items That Measure More Than One Ability
420 Citations1985Mark D. Reckase
Journal of Applied PsychologyA revision of the Job Diagnostic Survey: Elimination of a measurement artifact.
393 Citations1987Jacqueline R. Idaszak, Fritz Drasgow
PsychometrikaA New Item Response Theory Modeling Approach with Applications to Unidimensionality Assessment and Ability Estimation
384 Citations1990William Stout
Applied Psychological MeasurementApplication of Unidimensional Item Response Theory Models to Multidimensional Data
240 Citations1983Fritz Drasgow, Charles K. Parsons
It appears that item response theory models can be applied to moderately heterogenous item pools under the conditions simulated here.
Applied Psychological MeasurementThe Discriminating Power of Items That Measure More Than One Dimension
228 Citations1991Mark D. Reckase, Robert L. McKinley
Journal of Applied PsychologyStudy of the measurement bias of two standardized psychological tests.
198 Citations1987Fritz Drasgow
Multivariate Behavioral ResearchEmpirical Comparison Between Factor Analysis and Multidimensional Item Response Models
175 Citations1991Dirk L. Knol, Martijn P. F. Berger
It is concluded that for multiddimensional data a common factor analysis on the matrix of tetrachoric correlations performs at least as well as the theoretically appropriate multidimensional item response models.
Multivariate Behavioral ResearchAn Empirical Study of Various Indices for Determining Unidimensionality
157 Citations1984John Hattie
A simulation is described that determines the adequacy of various indices as decision criteria for assessing unidimensionality in a set of items using a three-parameter, multivariate, logistic latent-trait model.
Multivariate Behavioral ResearchTesting Pattern Hypotheses On Correlation Matrices: Alternative Statistics And Some Empirical Results
140 Citations1980James H. Steiger
PsychometrikaA Comparison of Four Methods of Constructing Factor Scores
140 Citations1967Roderick P. McDonald, E. J. Burr
Applied Psychological MeasurementAssessing the Dimensionality of a Set of Test Items
126 Citations1986Ronald K. Hambleton, Richard J. Rovinelli
BiometrikaRobustness of statistical inference in factor analysis and related models
123 Citations1987Michael W. Browne
Journal of Educational StatisticsRefinements of Stout’s Procedure for Assessing Latent Trait Unidimensionality
121 Citations1993Ratna Nandakumar, William Stout
This article provides a detailed investigation of Stout’s statistical procedure (the computer program DIMTEST) for testing the hypothesis that an essentially unidimensional latent trait model fits observed binary item response data from a psychological test, finding that it may fail to perform as desired in the presence of guessing.
British Journal of Mathematical and Statistical PsychologyDimensionality, bias, independence and measurement scale problems in latent trait test score models
119 Citations1980Harvey Goldstein
British Journal of Mathematical and Statistical PsychologyFive decades of item response modelling
116 Citations1989Harvey Goldstein, Robert Wood
This paper looks at 50 years of IRM and finds a disappointing lack of advance, and it is shown how a linear model framework, involving different response transformations, unifies separate approaches to the study of test item responses.
Journal of Educational MeasurementTraditional Dimensionality Versus Essential Dimensionality
92 Citations1991Ratna Nandakumar
The American StatisticianThe Reporting of Computation-Based Results in Statistics
87 Citations1975David C. Hoaglin, David Andrews
The role of computers in statistics is sketched, the reporting of scientific experiments is discussed, and standards for computation based results are proposed.
Journal of Educational MeasurementAssessing Dimensionality of a Set of Item Responses‐Comparison of Different Approaches
62 Citations1994Ratna Nandakumar
British Journal of Mathematical and Statistical PsychologyThe analysis of patterned correlation matrices by generalized least squares
49 Citations1977Michael W. Browne
Applied Psychological MeasurementThree Approaches to Determining the Dimensionality of Binary Items
40 Citations1991Mary Roznowski, Ledyard R Tucker +1 more
Annual Review of PsychologyLatent Structure and Item Sampling Models for Testing
21 Citations1985Ross E. Traub, Y. Raymond Lam
Educational and Psychological MeasurementCHIDIM: A FORTRAN Program for Assessing the Dimensionality of Binary Item Responses Based on Mcdonald's Nonlinear Factor Analytic Model
18 Citations1997André F. De Champlain, Kezong Tang
CHIDIM, a FORTRAN computer program that calculates the approximate chi-square statistic, is described, which tests the null hypothesis that the off-iagonal elements of a residual correlation matrix are equal to zero after fitting an m-factor model to a set of item responses.
Applied Psychological MeasurementThe Effect of Test Length and IRT Model on the Distribution and Stability of Three Appropriateness Indexes
18 Citations1992Brian Noonan, Marvin W. Boss +1 more
Data Archiving and Networked Services (DANS)On the assessment of dimensionality in multidimensional item response theory models
16 Citations1990Martijn P. F. Berger, Dirk L. Knol
BiometrikaRobustness of Statistical Inference in Factor Analysis and Related Models
13 Citations1987Michael W. Browne
Assessing Dimensionality of a Set of Items - Comparison of Different Approaches
13 Citations1992Ratna Nandakumar
Assessing Test Dimensionality Using an Index Based on Nonlinear Factor Analysis.
11 Citations1991André De Champlain, Marc E. Gessaroli
The results suggest that the incremental fit index has the potential for use in the assessment of unidimensionality of test data and in the determination of the number of dimensions underlying a test.