The accuracy of normal approximations to the binomial test was evaluated with and without a continuity correction, regarding control of Type I errors and power. Both tests exhibited substantial power loss in comparison to the exact binomial test, although they are easier to apply and are sometimes desirable. (SLD)

This paper derives a formula for the square of the correlation coefficient in terms of its maximum possible value under rotation of the axes. An application of the formula to quick visual estimation of the correlation coefficient is provided. (TJH)

Test statistics based on the assumption that test scores are interval rather than ordinal quality data are questioned. New statistical techniques which do not rely on this assumption are presented. (JKS)

Two multivariate probability distributions, a generalized beta distribution and a generalized F distribution, are derived. Formulas for the moments of these distributions are given and an example of the bivariate generalized beta is presented. (Author/JKS)

Similarity between pairs of scores with a common mean and variance can be expressed in terms of the absolute differences between them. The distribution of such absolute differences between pairs of normally distributed scores with a common mean and variance is discussed, with procedures for calculating moments and areas within this distribution.…

Randomization tests involve generating all possible assignments of subjects to treatments in order to create a distribution of possible test statistics. The use of a premutation group to enhance the understanding and utility of randomization tests is discussed. (Author/JKS)

This article presents two criterion-referenced grading models (a binomial grading model and an arcsine grading model), and shows how they can be applied in classrooms. In both cases, grades can be assigned on the basis of a criterion-referenced test with systematic control of the possible errors of misclassification (Author/BW)

This study was concerned with the effects of reliability of observations, sample size, magnitudes of treatment effects, and the shape of the sampled population on the relative power of the paired samples rank transform statistic and Wilcoxon's signed ranks statistic. (Author/LMO)

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)

Glass's estimator of effect size, the sample mean difference divided by the sample standard deviation, is studied in the context of an explicit statistical model. The exact distribution of Glass's estimator is obtained and the estimator is shown to have a small sample bias. Alternatives are proposed and discussed. (Author/JKS)

Approximations to the distribution of a common form of effect size are presented. Single sample tests, confidence interval formulation, tests of homogeneity, and pooling procedures are based on these approximations. Caveats are presented concerning statistical procedures as applied to sample effect sizes commonly used in meta-analysis. (Author)

The problem of determining which of several populations has the largest mean is considered. The procedure described by Dudewicz and Dalal is extended to the case of unequal sample sizes. (JKS)

An alternative to Fisher's exact test and the chi-square test for homogeneity in two-by-two tables is developed. The method provides for Type I error rates which are closer to the stated alpha level than either of the alternatives. (JKS)

Rosenthan's (1979) concept of fail-safe N has thus far been applied to probability levels exclusively. This note introduces a fail-safe N for effect size. (Author)

Using computer simulation, parametric analysis of covariance (ANCOVA) was compared to ANCOVA with data transformed using ranks, in terms of proportion of Type I errors and statistical power. Results indicated that parametric ANCOVA was robust to violations of either normality or homoscedasticity, but practiced significant power differences favored…