Multidimensional scaling has recently been enhanced so that data defined at only the nominal level of measurement can be analyzed. The efficacy of ALSCAL, an individual differences multidimensional scaling program which can analyze nominal, ordinal, interval and ratio data is presented. (Author/JKS)

Investigated the effectiveness of a training procedure corresponding to a component analysis of a hypothesis-testing task in improving kindergarten children's problem-solving abilities. (Author/JMB)

Statistical procedures based on Bayesian estimation for obtaining estimates of a propensity (which would include estimates of proportions or relative frequencies) are described for the special case where the observer can only note whether the propensity exceeds or does not exceed a constant between 0 and 1. (JKS)

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)

The Shine-Bower single subject analysis of variance is extended from being applicable to only an even number of trials to being applicable to any number of trials. (Author/JKS)

The distribution of the likelihood ratio test for testing the reality of the covariance matrix of a complete multivariate normal distribution is investigated. (Author/RC)

Two studies with three-year-old children tested the hypothesis that, whereas errors of phenomenism predominate when children are asked about objects' real and apparent properties, errors of intellectual realism predominate when children are asked about objects' real and apparent identities. Results provided some support for the property-identity…

Author responds to critique by Daniel Griffiths (Educational Administration Quarterly v. 19, p. 201-21) by defending his work in three areas: derivation of hypotheses, testing of hypotheses, and erroneous attribution of assumptions. (JW)

Tests the relationship between the success of psychotherapeutic efforts and the client's expectation-reality discrepancy, i.e., as the number of disconfirmed expectations increases the possibility for successful psychotherapy (positive therapy outcomes and low drop out rates) decreases. (Author/RK)

This paper provides a rationale for using and sustaining rival hypotheses Web-based tools to promote students' understanding of the concepts of internal and external validity. Five major concerns are identified. The first is that, in their present form, the Web sites subsume the discussion of threats to validity under experimental designs, giving…

This paper provides examples of how one can use the research issue and the relationships between qualitative and quantitative research as a frame for instructing students and judging the quality of research. The emphasis is on validity estimates, also called legitimization techniques, with attention to the idea of a qualitative-quantitative…

A simple shortcut procedure for analysis of variance is presented using the means, standard deviations, and number of cases in each sample directly. (Author/NE)

Study was directed at determining the extent to which Type I error rate is affected by violations in the basic assumptions of the test based on the q statistic. (Authors/CB)

The ability of M. Levine's subset-sampling assumptions to account for the decrease in response latency following the trial of the last error was investigated by employing a distributed stimulus set composed of four binary dimensions and a procedure which required Ss to make an overt response in order to sample each dimension. (Author)