Educational and Psychological Measurement · 2008 · 42 citations · 17 references
Social SciencesEducational AssessmentEducational MeasurementItem Response TheoryMeasurement InvariancePsychometricsFactor AnalysisItem AnalysisPsychological TestingTest ReliabilityTest TheoryTest ValidityFactor Loading Equality TestingFactor Loading EquivalenceModel Error EstimationMulti-group Measurement ModelsScore-level Dif DetectionTesting Measurement Invariance
This study compares two confirmatory factor analysis methods on their ability to verify whether correct assignments of items to subtests are supported by the data. The confirmatory common factor (CCF) method is used most often and defines nonzero loadings so that they correspond to the assignment of items to subtests. Another method is the oblique multiple group (OMG) method, which defines subtests as unweighted sums of the scores on all items assigned to the subtest, and (corrected) correlations are used to verify the assignment. A simulation study compares both methods, accounting for the influence of model error and the amount of unique variance. The CCF and OMG methods show similar behavior with relatively small amounts of unique variance and low interfactor correlations. However, at high amounts of unique variance and high interfactor correlations, the CCF detected correct assignments more often, whereas the OMG was better at detecting incorrect assignments.
17
Coefficient Alpha and the Internal Structure of Tests
Lee J. Cronbach · Psychometrika · 1951 · 43.2K citations · Full text
Social Sciences, Educational Assessment, Educational Measurement +14
Review of Psychometric theory (2nd ed.).
Rosedith Sitgreaves · Contemporary Psychology · 1979 · 11.5K citations