Theta is a statistic which measures the degree to which a designated pattern successfully partitions a matrix of pre- and post-treatment ratings into regions typical of each of two treatments. In this paper, theta is extended to multivariate and multigroup cases. (Author/BW)

A general method for identifying the separate components of the Rod-and-Frame Test consists of correlating theoretical patterns of scores with obtained test scores of single subjects. The correlation test calculates probability values from the test data. In this way, fit can be determined between theoretical pattern and test scores. (Author/BW)

The performance of 91 first grade students was compared using three screening tests of articulation: the Templin-Darley Screening Test of Articulation, the Screening Deep Test of Articulation, and the Predictive Screening Test of Articulation. There was poor correlation between tests in terms of the particular individuals failed. (Author/SEW)

The National Teacher Evaluation Program has developed a competency test for teachers that is the result of extensive consultation with the profession, pretesting, and review. Plans for the future of the test are detailed. (MLF)

The author argues for an expanded notion of intellectual giftedness which would take into account a person's ability to deal with nonentrenched (unusual or strange) tasks and concepts. This conception of intelligence is seen to be closer to that of creativity. Measurement problems are cited. (CL)

The article reviews the different methods of test instructions used with deaf and hard-of-hearing populations. Included are reviews of the most common tests presently used, the most common test instruction modifications presently used, and the research on the effects of different methods of presenting test instruction on performance. (Author)

Procedures suggested by Joreskog for performing exploratory factor analysis were evaluated. An in-depth analysis of psychological test scores of junior high school students was conducted. Procedures using exploratory and confirmatory techniques were found to produce misleading results in some instances. (Author/DWH)

The need for multiple comparison procedures for repeated measures means employing a pooled estimate of error variance to conform to the sphericity assumptions of the design in order to provide a valid test is discussed. An alternative approach which does not require this assumption is presented. (Author/JKS)

This study investigates four widely used methods of collecting direct similarity judgments for nonmetric multidimensional scaling: rating scale, triads, rank order of pairs, and conditional rank order. (Author/PN)

Compared six effect size (ES) measures commonly used by gerontological researchers as these measures relate to one another in both the analysis of variance and multiple regression models. Also discusses three other issues involving ES measures: the ES of a contrast; orthogonal and nonorthogonal designs; and partial ESs. (Author/JAC)

Analyses of artificial data involving repeated, related binary measures to different samples suggest that Tideman's generalized chi-square statistic and conventional repeated-measures analysis of variance do not produce conflicting outcomes. Provided the appropriate assumptions are met, analysis of variance may provide a more versatile approach.…

A discrete trials, operant tracking and a descending series procedure for the determination of hearing levels with three profoundly retarded young adults previously diagnosed as untestable proved quite workable and may provide for improved hearing testing with "difficult to test" individuals. (Author)

Known results for testing and estimation problems for patterned means and covariance matrices with explicit linear maximum likelihood estimates are applied to the block compound symmetry problem. An example involving educational testing is provided. (Author/JKS)

Alternating least squares and optimal scaling are presented as two approaches to the quantitative analysis of qualitative data. A variety of statistical approaches to this problem are discussed. Three examples are presented. (JKS)

A new method is proposed for a simultaneous factor analysis of dichotomous responses from several groups of individuals. The method makes it possible to compare factor loading pattern, factor variances and covariances, and factor means over groups. Generalized least squares is used as the estimation procedure. (Author/JKS)