Methods are presented for comparing grades obtained in a situation where students can choose between different subjects. It must be expected that the comparison between the grades is complicated by the interaction between the students' pattern and level of proficiency on one hand, and the choice of the subjects on the other hand. Three methods…

A mental multiplication test, containing items written in Dutch, Spanish, and Roman numerals was administered to 286 Dutch students. Further instruction was given in either Spanish or Roman, and a subtest combining languages was given. The iterative logit method was found to be useful in detecting biased test items. (GDC)

A systematic method for compromise between absolute and relative examination standards is proposed. The passing score is assumed to be related to expected pass rate through a simple linear function. Results define a function relating the percentage of successful candidates given a specified passing score to the passing score. (Author/DWH)

Studied the use of grade point average as a missing data technique for unavailable grades in school grade records. Results of 2 studies, 1 involving 2,080 Dutch college students, and the other involving 446 Dutch college freshmen, show that alternative missing grade methods produced better and more consistent predictions than other missing data…

A study of the relationship between first-year results for 115 Dutch medical students and achievement during medical school was studied using an item-response theory model for the longitudinal measure of change with stochastic parameters (developed by Albers et al., 1989) indicates that a low rate of growth in the first year persists. (SLD)

With the nominal model of R. D. Bock as a framework, transformation matrices can be used to constrain the parameters of test item response categories to reflect their componential design. The approach is illustrated in a study of a spelling task completed by 385 Dutch third graders. (SLD)