Provides a sample of seven published studies in different disciplines that inappropriately generalized reliability coefficients involving several raters to scores generated by a single rater. Score reliability when only one rater is used for scoring is lower than the score reliability for which two raters are used. (SLD)

Studied the reporting preferences of editorial board members of four scholarly journals in education and psychology with regard to analytic practices in the fifth edition of the American Psychological Association "Publication Manual." Responses of 106 board members show the movement toward reform in research reporting practices. (SLD)

Examined the frequency of use of various types of reliability coefficients for a sample of 696 tests in a directory published by the American Psychological Association. Coefficient alpha was the overwhelming favorite, and several measures treated almost universally in textbooks were rarely or never used. Identifies problems encountered in the…

Discusses reliability issues in light of recent studies and debates focused on psychometrics versus datametrics terminology and reliabilities generalization. Discusses the way multiple perspectives on score reliability may affect research practice, editorial policies, and reliability generalization across studies. (SLD)

The validity of the Slosson Intelligence Test (SIT) relative to the California Short Form Test of Mental Maturity and the Shipley-Institute of Living Scale was investigated on a sample of college students. Results supported the validity of the SIT. (Author/JKS)

G analysis is a data analytic method based on the G index of agreement. A generalized technique for the rotation of factors in G analysis in which marker variables are brought into alignment with their adjoining reference axis is presented. (Author/JKS)

A set of tables for determining tetrachoric correlations is presented. The coefficients have been determined to three-decimal accuracy. (JKS)

Identifies deficiencies in the new edition of the American Psychological Association's "Publication Manual," drawing on interviews with some critics and other parties. These include lack of follow-through with explanations and examples of how to report the statistics now recommended. (SLD)

Discusses four reasons for promoting the use of confidence intervals: (1) ease of interpretation; (2) links with familiar statistical tests; (3) promotion of meta-analytic thinking; and (4) increase of information about precision. Discusses calculations of confidence intervals for a basic standardized effect size measure and discusses software for…

Hermans' and Mehrabian's tests of achievement motivation were correlated with the achievement via conformance and achievement via independence scales of the California Psychological Inventory. The Mehrabian test was associated only with the achievement via conformance scale, but Hermans' measure was rather strongly related to both scales.…

The G index is a measure of similarity between pairs of dichotomized items. The G index is generalized here to the case where items are trichotomized. (JKS)

A problem in analysis of variance is that after rejection of the overall hypothesis, no contrasts of interest are found to be significant. A procedure for determining the contrast of significance is outlined, and the relationship between the "most significant" contrast and the overall test is shown. (Author/JKS)

A simple rationale for Scheffe's Method and Gabriel's Simultaneous Test Procedure is presented. Examples of both methods are provided. (Author)

The effect of stratified sampling of items based on item difficulty and/or interitem correlations on the estimation of test score distribution parameters using multiple matrix sampling was studied. Results indicated that stratification did not consistently improve the stability of parameter estimation. (Author/JKS)

An error is described that may occur in a posteriori testing, particularly when the original analysis of variance produces an F ratio that is just barely significant and the computer printout of the analysis does not provide the means that were used in the program. (Author/JKS)