Since we want to estimate the significance of a difference between two obtained scores, the first step is to calculate that difference. The Vocabulary subtest is described in Rapid Reference 4.8 the Information subtest assesses knowledge of common events, objects, places, and people. To illustrate the use of the standard error of the difference between scores, let us suppose we wish to estimate the statistical significance of the difference between Maria's obtained scores on two subtests of the WAIS-III: her Vocabulary subtest score of 15 and her Information subtest score of 10. Regardless of which of the two formulas is used the SEdiff will be larger than the SEM of either one of the scores involved in the comparison because the evaluation of differences between scores has to take into account the error present in both scores. It can be calculated using either one of the two formulas listed in Rapid Reference 4.9, depending on whether the scores to be compared are expressed on the same scale (Formula 1) or not (Formula 2). The statistic used for this purpose is the standard error of the difference between scores, or SEdiff. In both of these cases, reliability data may be used to derive probability statements concerning the likelihood that the obtained differences between scores-and what the scores represent-could have been due to chance. Assessment goals often entail comparisons (a) between two or more scores obtained by the same individual on different parts of a test battery, as when levels of performance in different domains are compared, or (b) between the scores of two or more persons on the same test, for the purpose of evaluating their relative merits or characteristics.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |