Derives formulas for the validity of predictor-criterion tests that hold for all test scores constructed according to the expected-value concept of true score. These more general formulas disclose some paradoxical properties of test validity under conditions where errors are correlated and have some implications for practical testing situations…

Results of recategorizing the Wechsler Intelligence Scale for Children (Revised) subtest scores of 159 black learning disabled primary grade children into spatial, conceptual, and sequential scales as recommended by A. Bannatyne led to the conclusion that the diagnostic utility of the Bannatyne recategorization is questionable. (Author/DB)

This paper reports the results of using several alternative methods of setting cut scores. The methods used were: (1) a variation of the Angoff method (1971); (2) a variation of the borderline group method; and (3) an advanced impact method (G. Dillon, 1996). The results discussed are from studies undertaken to set the cut scores for fourth grade…

Cloze testing and language performance is discussed as are two techniques for awarding partial credit: the quick performance measurement and feedback technique and the three-stage scoring hierarchy for partial credit. A figure and tables are included. (EJS)

Various aspects of the computerized adaptive testing (CAT) procedure for partial credit scoring were manipulated, focusing on the effects of the manipulations on operational characteristics of the CAT. The effects of item-pool size, item-pool information, and stepsizes used along the trait continuum were assessed. (TJH)

A recent multidimensional scaling analysis of the Test of English-as-a-Foreign-Language (TOEFL) item response data identified clusters of items in the test sections that, being more homogeneous than their parent sections, might be better for diagnostic use. The analysis was repeated using different scoring techniques. Results diverged only for…

Presents similarities and differences between the DSM-IV and empirically based approaches to behavioral and emotional problems. A case example illustrates the applications of the two approaches to school-based assessment. (Author/JDM)

Because there is no commonly accepted view of what makes for good writing, automated essay scoring (AES) ideally should be able to accommodate different theoretical positions, certainly at the level of state standards but also perhaps among teachers at the classroom level. This paper presents a practical approach and an interactive computer…

In a review of relevant literature, it is argued that correction for guessing formulas should not be used. It is contended that such formulas correct for guessing that does not really exist in a noticeable amount, penalize those students who have low self-esteem and self-confidence, correct for errors that are not necessarily errors, benefit risk…

The four scoring strategies compared were: lamda coefficients, chi-square weights, and two applications of multiple discriminant analysis. No significant differences were found when applied to the Kuder Occupational Interest Survey. (RC)

Leo Nedelsky developed a method for determining absolute grading standards for multiple choice tests. His method required a group of judges to examine each test question and eliminate those responses which the lowest D- student should be able to reject as incorrect. The correct answer probabilities remaining were used in computing an expected test…

This paper outlines a technique for differentially weighting options of a multiple choice test in a fashion that maximizes the item predictive validity. The rule can be applied with different number of categories and the "optimal" number of categories can be determined by significance tests and/or through the R2 criterion. Our theoretical analysis…

Seventeen statistics for measuring the reliability of criterion-referenced tests were critically reviewed. The review was organized into two sections: (1) a discussion of preliminary considerations to provide a foundation for choosing the appropriate category of "reliability" (threshold loss function, squared-error loss-function, or…

A method of interpolation has been derived that should be superior to linear interpolation in computing the percentile ranks of test scores for unimodal score distributions. The superiority of the logistic interpolation over the linear interpolation is most noticeable for distributions consisting of only a small number of score intervals (say…

One of the most important contentions of the Rasch model of item analysis is that two tests of the same trait, having some items in common, can be linked together using a "linking constant" derived from the common items. This would be accomplished by administering both tests to a sample of testees, calibrating the items of the tests…