An artifact encountered in regression models of human judgment is explored. The direction and magnitude of the artifactual effect is shown to depend upon the nature of the experimental task and task conditions. Use of an alternative index is recommended. (Author/JKS)

It is shown that if a behavior domain can be described by the common factor model with a finite number of factors, the squared correlation between the sum of a selection of items and the domain total score is actually greater than coefficient alpha. (Author/JKS)

A strict equivalence presupposed by Kaiser and Michael to derive the coefficient of "domain validity" is defensible only as a biased approximation. But then, it is far from clear what psychometric significance this coefficient has in the first place. (Author)

Joreskog's procedure for the analysis of simplex models was used to test Humphreys' assertion that eight semesters of undergraduate grade point averages have a simplex form. The assertion was confirmed, and precise estimates of unattenuated correlations and reliabilities were also obtained. (Author/JKS)

Three approaches to the prediction of juvenile recidivism--factor analysis, stepwise multiple regression, and stepwise discriminant analysis--are contrasted. Stepwise discriminant analysis provided the most consistent selection of variables in the data set used. Problems and advantages of the three approaches are discussed. (Author/JKS)

Stable factors of student ratings of teachers have been found under a variety of settings. The author suggests that these factors are artifacts of the raters' implicit categories of teaching behaviors and are not necessarily reflective of the behaviors themselves. (JKS)

The conceptual differences between coded regression analysis and traditional analysis of variance are discussed. Also, a modification of several SPSS routines is proposed which allows for direct interpretation of ANOVA and ANCOVA results in a form stressing the strength and significance of scrutinized relationships. (Author)

An overview of generalizability theory and a FORTRAN computer program for studying the generalizability of scores in a three facet, four factor design are presented. An illustrative example is presented. (Author/JKS)

An algorithm for item analysis in which item discrimination indices have been defined for the distractors as well as the correct answer is presented. Also, the concept of convergent and discriminant validity is applied to items instead of tests, and is discussed as an aid to item analysis. (Author/JKS)

A general factor analysis computer algorithm is briefly discussed. The algorithm is highly transportable with minimum limitations on the number of observations. Both singular and non-singular data can be analyzed. (Author/JKS)

Earlier comparisons of packaged programs for factor analysis are updated because of recent revision in some programs. The top status of SPSS is no longer so apparent as formerly. BMD and SAS now have expanded options. SAS has flexibility and convenience. (Author)

A computer program for a comparative evaluation of the extent of item bias between two subgroups in a test population is described. The program calculates an index of bias based on Angoff's elliptical distance measure, and provides statistics for determining the similarity of intergroup item parameters. (Author/JKS)

Confidence scored tests allow subjects to respond to the options on a multiple choice test by assigning probabilities to each of the item options. This paper describes an interactive FORTRAN computer program used for administering, scoring, and interpreting the results of confidence scored tests. (Author/JKS)

ANALYSIS, a FORTRAN computer program developed as an aid to investigation of and instruction in the psychometric properties of test items, is described. The program utilizes both correlational and analysis of variance approaches to classical item analysis. (Author/JKS)

A general FORTRAN computer program for analyzing categorical or frequency data obtained from questionnaires is described. A variety of descriptive statistics, chi square, Kendall's tau and Cramer's statistic are provided. (Author/JKS)