Presents the strategic advantages of focused over omnibus tests of statistical significance in counseling research, and demonstrates the utility of interpreting the magnitude of the effect as a way of assessing practical significance (i.e., in addition to computing "p" levels). Gives simple procedures for computing effect size using the…

Subroutines to calculate exact chi square and Fisher's exact probability tests are presented for 3 by 2 cross-classification tables. A nondirectional probability value for each test is computed recursively. (Author/GDC)

This paper proposes a new typology for understanding common research errors that expands on the four types of error commonly discussed in the research literature. Examples are presented to illustrate Type I and Type II errors, errors related to the interpretation of statistically significant and nonsignificant results respectively, with attention…

A program for calculating Kendall's tau-a, tau-b, partial tau, coefficient of concordance, coefficient of consistence, and coefficient of agreement is presented. In addition, the program provides tests of significance for each of the coefficients except partial tau. (DG)

A concise table is presented based on a general measure of magnitude of effect which allows direct determinations of statistical power over a practical range of values and alpha levels. The table also facilitates the setting of the research sample size needed to provide a given degree of power. (Author/CM)

Psychophysicists neglect to consider how error should be characterized in applications of the power law. Failures of the power law to agree with certain theoretical predictions are examined. A power law with lognormal product structure is proposed and approximately unbiased parameter estimates given for several common estimation situations.…

Two r coefficients of association are discussed. One of the coefficients can be applied to any nonparametric test statistic (NTS) in which a normal approximation equation is appropriate. The other coefficient is applicable to any NTS in which exact probabilities are known. (Author/RL)

Order analysis, a technique to isolate unidimensional hierarchies representing multidimensional structure of binary data, is reviewed. Several theoretical flaws inherent in the probalistic version are presented. Suggestions of possible directions for future research are offered. (Author)

The procedures yielding confidence intervals for maximized alpha coefficients of Joe and Woodward are reviewed. Confidence interval procedures of Whalen and Masson are next reviewed. Results are then presented of a Monte Carlo investigation of the procedures. (Author/CTM)

Sixteen tables are presented for critical values of the larger of two sample correlation coefficients from two independent samples, given the sample size and the value of the smaller correlation. These tables allow quick assessment of significance without requiring calculation of the test statistic. (SLD)