Literaturnachweis - Detailanzeige
Autor/inn/en | Angoff, William H.; Cowell, William R. |
---|---|
Institution | Educational Testing Service, Princeton, NJ. Graduate Record Examination Board Program. |
Titel | An Examination of the Assumption that the Equating of Parallel Forms is Population-Independent. |
Quelle | (1985), (92 Seiten)
PDF als Volltext |
Sprache | englisch |
Dokumenttyp | gedruckt; online; Monographie |
Schlagwörter | Aptitude Tests; College Entrance Examinations; Equated Scores; Error of Measurement; Higher Education; Intellectual Disciplines; Item Analysis; Mathematics Tests; Sampling; Student Characteristics; Test Construction; Test Interpretation; Testing Problems; Verbal Tests; Weighted Scores; Graduate Record Examinations |
Abstract | Linear and equipercentile equating conversions were developed for two forms of the Graduate Record Examinations (GRE) quantitative test and the verbal-plus-quantitative test. From a very large sample of students taking the GRE in October 1981, subpopulations were selected with respect to race, sex, field of study, and level of performance (defined by GRE analytical test scores). The variance error of equated scores between the forms was calculated, and conversions were made between the test forms. Departures of the conversions, based on each of these special samples from the population conversion, were calculated and evaluated in terms of the standard error of equating at five selected raw score points on Form D3, adjusted for disparity between the means, as well as variance, skewness, and kurtosis for these populations and the corresponding total populations. The conversions for the Physical Science subpopulation were significantly different from the total population. When adjustments were made for variance, skewness, and kurtosis, these conversions fell in line for the homogeneous GRE quantitative test, but not so clearly for the heterogeneous verbal-plus-quantitative test. Conversions for all other subpopulations were acceptably within range. The assumption of population-independence for equating was supported for homogeneous but not heterogeneous tests. (Author/GDC) |
Erfasst von | ERIC (Education Resources Information Center), Washington, DC |