Comparing variability of test scores across alternate forms, test conditions, or subpopulations is a fundamental problem in psychometrics. A confidence interval for a ratio of standard deviations is proposed that performs as well as the classic method with normal distributions and performs dramatically better with nonnormal distributions. A simple…

The indices of item difficulty and discrimination, the coefficients of effective length, and the average item information for both single- and multiple-answer items using six different scoring formulas were computed and compared. These formulas vary in terms of the assignment of partial credit and the correction for guessing. (Author/BW)

In a study to determine whether a shift from Formula scoring to Rights scoring can be made without causing a discontinuity in the test scale, the analysis of special administrations of the Scholastic Aptitude Test and Chemistry Achievement Test and the variable section of an operational form of the Graduate Management Admission Test (GMAT) is…

This study tested for cultural bias in the Bender Visual Motor Gestalt Test. Subjects were 72 black and white patients diagnosed as either brain damaged or psychiatric. Bender protocols were scored by Pascal-Suttell and Hain systems. No race effect appeared except for the Pascal-Suttell system for which blacks scored significantly better. (Author)

Showed that the standard score difference method for determining intelligence quotient achievement discrepencies produced disproportionate racial representation, whereas the regression method produced proportionate racial representation in Learning Disabilities (LD) classes. Demonstrated advantages in measurement of discrepancies, LD program…

Several applications of latent trait models in reading research are discussed, their nature reviewed, and two experiments presented as heuristic applications of the Rasch Model. Two studies of children's comprehension of selected anaphoric structures in prose were performed using both conventional and Rasch Model analyses. Twenty-six children…

A novel scoring procedure was investigated in order to obtain scores from a conventional multiple-choice test that would be free of the guessing component or contain a known guessing component even though examinees were permitted to guess at will. Scores computed with the experimental procedure are based not only on the number of items answered…

Problems which arise when criterion referenced test results are used to evaluate the effects of an elementary school reading program are discussed. Topics include: alternative methods of analyzing test results, sensitivity of the instrument to program outcomes, and comparison of criterion referenced and norm referenced achievement test data.…

A statistical comparison of Medical College Admission Test scores with National Board of Medical Examiners (NBME) Part I scores of one school's students supported simple averaging of subtest scores rather than weighting as a predictor of NBME Part I performance. Similar results were obtained using basic science course examination scores. (MSE)

Investigates whether training raters to interpret the scoring dimensions on a rubric would increase reliability. Compares two groups of kindergarten and first-grade teachers: one group with training, one without. Finds that training increases raters' abilities to reliably interpret scoring items. (SC)

Effects of logically weighting incorrect item options in conventional tests and different scoring functions with confidence tests on reliability and validity were examined. Ninth graders took conventionally administered Verbal and Mathematical Reasoning tests, scored conventionally and by a procedure assigning degree-of-correctness weights to…

A comparison of reliability and validity was made for three testing procedures: 1) responding conventionally to Verbal Ability and Mathematical Reasoning tests; 2) using a confidence weighting response procedure with the same tests; and 3) using the elimination response method. The experimental testing procedures were not psychometrically superior…

This study empirically determined the optimizing weight to be applied to the Wrongs Total Score in scoring rubrics of the general form = R - kW, where S is the Score, R the Rights Total, k the weight and W the Wrongs Total, if reliability is to be maximized. As is well known, the traditional formula score rests on a theoretical framework which is…

A comparison of four frequently used standard setting methods for deriving cut-off scores with respect to the expected performance of minimally competent students, is presented in this paper. Ten Kansas Competency Based Tests, in reading and mathematics, were administered across five grade levels in a state-wide minimal competency testing program.…