A statistical framework for investigating various regression approaches to linear composites is presented in this monograph. The consequences of variance approaches for psychometric theory are discussed. (A six-page bibliography is appended). (JKS)

Presented is an approach to introducing upper division, undergraduate geology students to nonparametric statistics and their application to geologic data. Discussed are the use of the Mann-Whitney U and the Kolmogorov-Smirnov tests and a class assignment which illustrates their use. (CW)

Nonparametric item response models were used to investigate psychometric properties of the Beck Depression Inventory in 648 depressed outpatients and 1,182 nonpatient college students. Estimated values for some options did not align with a priori weights in the college sample, and some option characteristic curves were problematic in both samples.…

Describes primary and supplemental textbooks on nonparametric statistics. Lists conceptual and applied articles using these techniques. Recommends using the Statistical Package for the Social Sciences (SPSS-X) computer statistical analysis program. (CFR)

Discusses the educational uses of computer games and simulations and describes a study conducted at the State University of New York College at Farmingdale that used the computer game "Sim City 2000." Highlights include whole systems learning, problem solving, student performance, nonparametric statistics, and treatment of experimental…

In a growing number of countries, government-appointed assessment panels develop ranks on the basis of the quality of scholarly outputs to apportion budgets in recognition of evaluated performance and to justify public funds for future R&D activities. When business and management journals are being grouped in broad quality categories, a recent…

DETECT, the acronym for Dimensionality Evaluation To Enumerate Contributing Traits, is an innovative and relatively new nonparametric dimensionality assessment procedure used to identify mutually exclusive, dimensionally homogeneous clusters of items using a genetic algorithm ( Zhang & Stout, 1999). Because the clusters of items are mutually…

Sampling distributions for ten tests for comparing population variances in a two group design were generated for several combinations of equal and unequal sample sizes, population means, and group variances when distributional forms differed. The ten procedures included: (1) O'Brien's (OB); (2) O'Brien's with adjusted degrees of freedom; (3)…

Statistical sampling techniques for the measurement of book readership within libraries are described. The procedures, developed and initially implemented at Rider College, rely upon interviews of book readers inside the library rather than upon such indirect usage measures as which volumes are lift on tables for reshelving, or analyses of user…

A Monte Carlo technique was used to investigate the small sample goodness of fit and statistical power of several nonparametric tests and their parametric analogues when applied to data which violate parametric assumptions. The motivation was to facilitate choice among three designs, simple random assignment with and without a concomitant variable…

A procedure--based on item response theory--for testing the hypothesis of unidimensionality of the latent space is proposed. Use of the procedure is supported by an asymptotic theory and a Monte Carlo simulation study. The procedure tests for unidimensionality in test construction and/or compares two tests. (SLD)

A detailed investigation is provided of Stout's statistical procedure (the computer program DIMTEST) for testing the hypothesis that an essentially unidimensional latent trait model fits observed binary item response data from a psychological test. Three refinements achieve greater power. The revised approach is validated using real data sets.…

Three methods for the estimation of the reliability of single dichotomous items are discussed. All methods are based on the assumptions of nondecreasing and nonintersecting item response functions and the Mokken model of double monotonicity. Based on analytical and Monte Carlo studies, it is concluded that one method is superior to the other two…

DIMTEST is a statistical test procedure for assessing essential unidimensionality of binary test item responses. The test statistic T used for testing the null hypothesis of essential unidimensionality is a nonparametric statistic. That is, there is no particular parametric distribution assumed for the underlying ability distribution or for the…

This study compared five density estimation techniques applied to samples from a population of 272,244 examinees' ACT English Usage and Mathematics Usage raw scores. Unsmoothed frequencies, kernel method, negative hypergeometric, four-parameter beta compound binomial, and Cureton-Tukey methods were applied to 500 replications of random samples of…