A modification of the SIBTEST procedure to assess differential item functioning (DIF) for two-dimensional test data (i.e., data for tests where two intended abilities are tapped by test items) is described. A small simulation study is carried out to assess the performance of the modified SIBTEST to detect DIF in such two-dimensional data. The…

The Behrens-Fisher problem arises when one seeks to make inferences about the means of two normal populations without assuming the variances are equal. This paper presents a review of fundamental concepts and applications used to address the Behrens-Fisher problem under fiducial, Bayesian, and frequentist approaches. Methods of approximations to…

Magnitude of effect (ME) statistics are an important alternative to statistical significance. Why methodologists encourage the use of ME indices as interpretation aids is explained, and different types of ME statistics are discussed. The basic concepts underlying effect size measures are reviewed, and how to compute them from published reports…

Aptitude-treatment interaction (ATI) studies have been used with some frequency, yet many researchers do not understand fully what interaction effects are. Because the means for interactions involve fewer persons per mean, power to detect interaction effects is typically smallest for the highest-order interaction in a given design. This phenomenon…

Proposes three different multiple range tests based upon the Newman-Keuls philosophy with respect to significance levels. The three tests utilize the Fmax statistic, Cochran's statistic and a normalizing log transformation of the sample variances respectively. (Author/RC)

The following article provides a brief primer and overview of multilevel and hierarchical linear modeling. The school-effects model with random effects is illustrated with a heuristic dataset. Finally, recommendations are presented for researchers studying learning disabilities who would like to utilize this methodology.

The use of a university exam to test the effects of ESP produced essentially overlapping distributions of performances by the experimental and control groups. (Author/KM)

A Bayesian analysis for 2 to the k power factorial arrangements of treatments is presented in this paper. To perform the analysis, an experimenter must specify prior distributions on an orthogonal set of linear functions representing the main effects and interactions and on a function representing the grand mean. The solution is relatively…

The standard statistical analysis of data classified in two ways (say into rows and columns) is through an analysis of variance that splits the total variation of the data into the main effect of rows, the main effect of columns, and the interaction between rows and columns. This paper presents an alternative Bayesian analysis of the same…

Although the Statistical Package for the Social Sciences (SPSS) contains no subprogram that is complete in itself for analyzing repeated measures or mixed designs analysis of variance, subprogram ANOVA can be used to obtain almost all the required sums of squares for repeated measures designs, mixed designs having repeated measures on some…

A TV AND A CONVENTIONAL (C1) COMPANY OF 156 ARMY TRAINEES WERE FORMED BY MATCHING THEIR APTITUDE SCORES ON THE ARMED FORCES QUALIFICATION TEST. A REVIEW-PREVIEW INSTRUCTIONAL TECHNIQUE WAS USED FOR BOTH COMPANIES, AND FOR OTHER CONVENTIONAL COMPANIES (C2-C8) SELECTED TO PROVIDE INFORMATION SUCH AS AWARENESS OF MEASUREMENT. IN 25 COMPARISONS OF…

The robustness of the statistic for complex contrasts in analysis of variance is compared to the statistic developed by Welch. The Welch statistic is recommended as the benchmark test for complex contrasts. (Author/JKS)