The Impact of Using Item Parcels on ad hoc Goodness of Fit Indices in Confirmatory Factor Analysis: An Empirical Example.Report as inadecuate




The Impact of Using Item Parcels on ad hoc Goodness of Fit Indices in Confirmatory Factor Analysis: An Empirical Example. - Download this document for free, or read online. Document in PDF available to download.





The Arabic version of I. G. Sarason's (1984) Reactions to Tests scale was used to examine the impact of using item parcels on ad hoc goodness of fit indices in confirmatory factor analysis. Item parcels with different numbers of items and different numbers of parcels per factor were used. Analyses were conducted on a sample of 420 tenth graders from 2 similar Israeli-Arab high schools. Model fit was examined in terms of chi square, chi square to degrees of freedom ratio, the goodness-of-fit index (GFI), the comparative fit index (CFI), the Tucker-Lewis index (TLI), and the single sample expected cross-validation index (ECVI). Model fit in terms of GFI, CFI, TLI, and ECVI systematically improved when the number of items per parcel increased. The P value associated with chi square indicated the same tendency. However, the chi square to degrees of freedom ratio did not change systematically. The analyses were repeated with another sample consisting of 374 tenth graders from the same 2 high schools. Basically, the results were the same as those of the first sample. (Contains 2 figures, 6 tables, and 20 references.) (Author/SLD)

Descriptors: Arabic, Chi Square, Foreign Countries, Goodness of Fit, Grade 10, High School Students, High Schools, Measurement Techniques, Student Attitudes, Test Anxiety











Author: Takahashi, Tomone; Nasser, Fadia

Source: https://eric.ed.gov/?q=a&ft=on&ff1=dtySince_1992&pg=12510&id=ED398279







Related documents