Literaturnachweis - Detailanzeige
Autor/inn/en | Holland, Paul W.; Thayer, Dorothy T. |
---|---|
Institution | Educational Testing Service, Princeton, NJ. Program Statistics Research Project. |
Titel | An Alternate Definition of the ETS Delta Scale of Item Difficulty. Program Statistics Research. |
Quelle | (1985), (17 Seiten)
PDF als Volltext |
Sprache | englisch |
Dokumenttyp | gedruckt; online; Monographie |
Schlagwörter | Difficulty Level; Error Patterns; Estimation (Mathematics); Item Analysis; Mathematical Models; Predictive Validity; Scaling; Test Items |
Abstract | An alternative definition has been developed of the delta scale of item difficulty used at Educational Testing Service. The traditional delta scale uses an inverse normal transformation based on normal ogive models developed years ago. However, no use is made of this fact in typical uses of item deltas. It is simply one way to make the probability scale of item difficulty a more useful set of units that are not compressed near 0 or 1. The alternative scale uses a different function to achieve the same result. Both a logistic definition and a normal definition can be calculated. For item difficulty between .10 and .90, the difference between the standard definition of the delta scale and one based on the logistic distribution is negligible. The logistic definition scales very easy items as easier than the normal definition. This change in the delta scale, as compared with the traditional delta, would have little effect on the values of the statistics used. However, it offers the advantage of the use of logits. Also, differences in item deltas (e.g., for a comparison of two subpopulations' performance on an item) can be interpreted in terms of odds-ratios of the corresponding difficulty values. (GDC) |
Erfasst von | ERIC (Education Resources Information Center), Washington, DC |