An examination was made of a large number of GATB validation studies to determine the frequency of nonlinear relationships. The number of significantly nonlinear relationships fell very close to the chance level; about 5 per cent were significant at the .05 level and 1 per cent were significant at the .01 level. (Author)

Tables are presented giving the critical values of the biserial and the point biserial correlation coefficients (when the null hypothesis assumes a value of zero for the coefficient) at the 0.05 and the 0.01 levels of significance. (Author)

The form of the Johnson-Neyman region of significance is shown to be determined by the statistic for testing the null hypothesis that the population within-group regressions are parallel. Results are obtained for both simultaneous and nonsimultaneous regions of significance. (Author)

The G index is a measure of the similarity between individuals over dichotomous items. Some tests for the G-index are described. For each case an example is included. (Author/GK)

This paper demonstrates that multiple comparison tests using a pooled error term are dependent on the circularity assumption and shows how to compute tests which are insensitive (robust) to this assumption. (Author/GK)

If the null hypothesis of a one-sample test of multivariate means is rejected, the dimension of the line joining the population centroid and the hypothesized centroid can be interpreted with a linear function, using a discriminant function and the correlation of each dependent variable with a discriminant score. (Author/BW)

Communication researchers have recently expressed concern with the lack of statistical power in their literature. Authors propose a method for increasing statistical power: the partitioning of the decision region in three parts. This procedure results in an unambiguous interpretation of nonsignificant results and leads to increased power. (PD)

Cattell's scree test and Bartlett's chi-square test for the number of factors to be retained from a factor analysis are shown to be based on the same rationale, with the former reflecting subject sampling variability, and the latter reflecting variable sampling variability. (Author/JKS)

Errors of misclassification associated with two concept acquisition criteria and their effects on the actual significance level and power of a statistical test for sequential development of these concepts are presented. Explicit illustrations of actual significance levels and power values are provided for different misclassification models.…

Procedures are developed for testing the hypothesis that Cronbach's alpha reliability coefficient is equal for two tests given to the same subjects. (Author/JKS)

The authors contend that most research in education lacks statistical power. They feel that the poor use of statistics as a tool for enhancing internal validity must be remediated. The adoption of a new convention is proposed in order to put statistical certainty into reasonable perspective. (RLV)

The Johnson-Neyman technique is briefly reviewed, and a program for carrying out an analysis using the procedure is described. The program accommodates one independent and one dependent variable, up to 20 groups of observations, and an unlimited number of cases. (Author)

Summarizes the post-1994 literature in psychology and education regarding statistical significance testing, emphasizing limitations and defenses of statistical testing and alternatives or supplements to statistical significance testing. (SLD)

Provided initial assessment of the statistical power of rehabilitation counseling research published in selected rehabilitation journals. From 5 relevant journals, found 32 articles that contained statistical tests that could be power analyzed. Findings indicated that rehabilitation counselor researchers had little chance of finding small…