Multivariate models are demonstrated to analyze repeated measures profile and growth curve data when univariate or multivariate mixed model assumptions are not tenable. Standard mixed model tests are recovered from certain multivariate hypotheses. The procedures are illustrated using numerical examples. (Author/RC)

Multiple matrix sampling is a psychometric procedure in which a set of test items is subdivided randomly into subtests of items with each subtest administered to different subgroups of examinees selected at random from the examinee population. Although each examinee receives only a proportion of the complete set of items, the statistical model…

To resolve a recent controversy between Klein and Cleary and Levy, a model for dichotomous congeneric items is presented which has mean errors of zero, dichotomous true scores that are uncorrelated with errors, and errors that are mutually uncorrelated. (Author)

The construction and validation of a learning hierarchy designed to assist instruction in the skills of science hypothesis formation and testing are described. Results of the validation using prospective elementary teachers are described, and the revised hierarchy is presented. Revalidation results for a different group of teacher trainees are…

This project was designed to test the hypothesis that "variation in quantity of practice in writing, when all other relevant factors are held constant, will result in variation of ability to write." Writing was limited to expository writing, and the factors held constant were quality of instruction, ability of students, and evaluation procedures…

Bayesian statistical inference is unfamiliar to many educational evaluators. While the classical model is useful in educational research, it is not as useful in evaluation because of the need to identify solutions to practical problems based on a wide spectrum of information. The reason Bayesian analysis is effective for decision making is that it…

Although analysis of variance is the most popular statistical tool to researchers in the behavioral sciences, the casual user has recognized only recently that there is no single correct way to perform such an analysis. This paper is concerned with hypotheses tested in the two-way, fixed model under a variety of conditions: (1) with and without…

The argumentative perspective enables rhetoric to function in a manner analagous to science or analytic philosophy, yielding reliable knowledge about nonempirical topics, which other methods cannot address. In short, argumentation is the equivalent of hypothesis-testing. Forensics should offer laboratory experience in developing this perspective…

A table of critical values is presented for use with Chacko's ordered alternatives test for the analysis of variance. (Author/JKS)

Procedures for carrying out a Shine Combined (repeated measures) Analysis of Variance (ANOVA) when there are unequal group sizes are described. (Author/JKS)

The conduct of multiple post hoc comparison procedures following an analysis of variance is discussed. Various procedures are contrasted in terms of appropriateness, power, and other features. Octhogonal and nonorthogonal comparisons are discussed. (JKS)

The basic assumption of Cooper's nonparametric test for trend (EJ 125 069) is questioned. It is contended that the proper assumption alters the distribution of the statistic and reduces its usefulness. (JKS)

In numerous applications of the analysis of variance, it is necessary to compute the power of F tests having numerically high alpha (significance) levels. This article tabulates the power of F tests for a variety of degrees of freedom. (Author/JKS)

A specially designed discrimination learning task was used to investigate whether the performance of kindergarten and first grade children could be improved through explicit training with a simple hypothesis-testing strategy. (Author/MP)

Several ways of using traditional analysis of variance to test the homogeneity of variance in factorial designs with equal or unequal cell sizes are compared using theoretical and Monte Carlo results. (Author/JKS)