Four testing procedures for establishing the number of non-zero population roots in canonical analysis are investigated. Results of a Monte Carlo study indicate that three well-established procedures were effective, and a new procedure designed to correct a supposed flaw in the other procedures was ineffective. (JKS)

Techniques are developed for constructing confidence regions for each of the points in a multidimensional scaling solution. Bayesian credibility regions are discussed, and a technique for displaying these regions is described. (Author/JKS)

The relationship between variables in applied and experimental research is often investigated by the use of extreme groups. Recent analytical work has provided an extreme group procedure that is more powerful than the standard correlational approach. The present article provides procedures to optimize power and thusly resources in such studies.…

A series of independent, normally distributed events may be broken into intervals on an a priori basis. Then, within interval variance may be compared to among interval variance. These might be considered short-term and long-term variances. This concept and a test for comparing variances are presented. (Author/JKS)

Two potentially useful tests for homogeneity of variance--the jackknife test and the Box test--are described and compared. Recommendations for the use of these techniques and computational examples of each are provided. (Author/JKS)

Discusses the relation between discrimination and identification performance, particularly with regard to experiments with speech and other signals used to draw a distinction between continuous and categorical perception. Offers three main arguments. (Author/RK)

Measurement error in dependent variables reduces the power of statistical tests to detect mean differences of specified magnitude. Procedures for determining power and sample size that consider the reliability of the dependent variable are discussed and illustrated. Methods for estimating reliability coefficients used in these procedures are…

The asymptotic power of the Cramer-von Mises test when parameters are estimated from the data is studied under certain local (contiguous) alternatives. Notion of (asymptotic) direction and distance from the null hypothesis of alternatives is introduced, and it is shown that there exist directions with maximum, minimum, and arbitrary intermediate…

Some objections (EJ 156 226) to an earlier article of mine (EJ 123 711) concerning the use of hypothetical moral situations in moral education are first examined. It is then argued that to characterize morality as a wholly "public" or "private" affair is mistaken, as moral decision-making must involve a combination of both…

A total of 20 children between seven and 11 years of age and 20 adults categorized rules of perceived high social utility in social conventional terms in both public and private contexts; but they categorized rules of perceived low social utility in social conventional terms in private contexts and in personal terms in public contexts. (RH)

The hypothesis testing abilities of 15 language impaired and 15 normally developing children matched for mental age were investigated using discrimination-learning tasks. Findings indicated the impaired children performed poorer than non-impaired children especially on the nonexplicit problems suggesting the deficits may be related to difficulties…

The logic and procedures underlying a disturbance term regression test of logical consistency for structural models are reviewed for recursive and nonrecursive designs. It is shown that in a simple three-variable, complete mediational case the test procedure is mathematically equivalent to a part correlation. (Author/LMO)

A general procedure is provided for comparing correlation coefficients between optimal linear composites. It allows computationally efficient significance tests on independent or dependent multiple correlations, partial correlations, and canonical correlations, with or without the assumption of multivariate normality. Evidence from Monte Carlo…

When the experimental units are measured twice, and the response variable is dichotomous, the equality of the two proportions is usally assessed by Mc Nemar's (1947) test. In this paper, Bayesian methods are presented for testing hypotheses regarding the two success probabilities in light of complete and incomplete data. (Author/BW)

Responds that hypothesis testing is not a formula for judging debates but an attempt to model the nature of argumentation itself. Addresses criticisms of hypothesis testing and the role of paradigms in argumentation theory and practice. (PD)