A new type of scale, called the bipolar ordinate scale, is defined with assumptions slightly stronger than those of the normal ordinal scale. The scale would be used for affective type measurement. The logic behind the scale and examples are presented. (Author/JKS)

Judgment analysis is a technique for examining the behavior of judges in rating subjects on a single attribute. This paper presents the multivariate analogue to that technique, which consists of rating subjects on several attributes. The logic of the extension and an example are presented. (JKS)

Procedures for the Rasch model, sample free item calibration are reviewed and compared for accuracy. The theoretically ideal procedure is shown to have practical limitations. Two alternatives to the ideal are presented and discussed. A correction for bias in the most widely used alternative is presented. (Author/JKS)

Bechhofer's procedure for selecting the population with the largest mean from among several populations with known variances is discussed as it applies to the problem of selecting the bivariate normal population with the largest correlation coefficient. Tables of appropriate sample sizes are provided and an example is discussed. (Author/JKS)

The Activity Vector Analysis is a short personality measure, widely used in industry for personnel selection, placement and assessment. This paper questions the statistical basis of the measure as it has appeared in the literature. Recommendations are made for revision of the measure and for resolution of theoretical incongruencies. (Author/JKS)

Product correlation was studied under the condition that the original variables are jointly distributed multivariate normal with equal coefficients of variation. Product correlation was shown to range between the two extremes of sum correlation and either the value zero or an unfamiliar function of the intercorrelations of the original variables.…

Logical estimates of item difficulty made by judges were compared to empirical estimates derived from a test administration. Results indicated substantial correspondence between logical and empirical estimates, and substantial variation among judges. Further, the more elaborate the system used by judges to make estimates, the more accurate the…

Descriptions from men and women subjects of sex stereotypes using the Adjectives Check List and the favorability of stereotypical adjectives were investigated. Results showed highly similar stereotypes for both men and women subjects and no differences in overall favorability in male and female stereotypes. (Author/JKS)

The problem of demonstrating invariance of factor structures across criterion groups is addressed. Procedures are outlined which combine the replication of factor structures across sex-race groups with use of the coefficient of invariance to demonstrate the level of invariance associated with factors identified in a self concept measure.…

The intercorrelations among the twelve subtests of the WISC were analyzed for each of eleven age groups in the standardization sample, using the principal factor method. Both the two and three factor solutions are assessed using the coefficient of congruence. (Author/JKS)

A group peer rating technique was employed to develop reliable measures of sixteen personality traits for adult workers and high school seniors. Several of these traits were found to have high predictive validity for pay differentials, supervisor's ratings, and school grades. (Author/JKS)

The effectiveness of various tailored testing strategies for use in objective based instructional programs was investigated. The three factors of a tailored testing strategy under study with various hypothetical distributions of abilities across two learning hierarchies were test length, mastery cutting score, and starting point. (Author/JKS)

The Internal-External Locus of Control Scale was modified to a Likert-type scale and subjected to a principal components analysis and varimax rotation on a sample of subjects. Four factors were extracted which were then related to other personality measures on the same sample. (JKS)

This study investigated the relationship between response style in college course evaluation and cognitive complexity of respondent. A significant relationship was found between a measure of cognitive complexity and within subject variance on the course evaluation instrument. (Author/JKS)

Interscal is a program for subject-computer interactive multidimensional scaling. The program analyzes subsets of judgments of similarity as they are given and picks out dimension-defining stimuli; this capability allows for a great reduction in the number of judgments. Program features and options are described. (Author)