Configural frequency analysis (CFA), a new method for identifying types, is illustrated numerically. Relations to latent class analysis and to factor analysis are discussed. It is suggested to use CFA as a type-defining method instead of factor analysis if the variables are linked not only by first but also by higher-order associations. (RC)

Develops and illustrates a method for clustering hierarchically the interrelationships between many persons, as represented in a matrix of a thousand by a thousand. (RC)

Methods for analyzing the multitrait-multimethod matrix are reviewed and the results of their application to a classic data set are compared. It is shown that different analysis methods can yield different validity conclusions, and that the results obtained are partly dependent on the subjective judgments of the users. (Author/RC)

Major interest is the derivation of a mathematical formulation and a demonstration of the effects of pooling two subgroups on the total group correlation coefficient, and additionally, a procedure to guide the decision concerning the pooling of data for the purpose of calculating a single correlation coefficient. (Author/RC)

A study was made of the r-point biserial coefficient using four non-normal distributions for the continuous variable: rectangular, bimodal-normal, bimodal-peaked and bimodal-peaked and skewed. (Author)

The controversy regarding the admissibility of one-tailed tests of hypotheses was examined. Rather than taking a stand with regard to whether the one-or the two-tailed test is the most seriously flawed, a procedure is developed which can capitalize on the advantages of each. (RC)

A new test for increasing or decreasing trend in a set of observations is presented. Rather than making specific paired comparisons, as in the Cox and Stuart tests for trend, the user of the new test makes the comparisons of all possible pairs of observations. (Author)

Estimates for the variances of empirically determined scoring weights are given. It is also shown that test item writers should write distractors that discriminate on the criterion variable when this type of scoring is used. (Author)

A method of applying the discriminant function to correlated samples was discussed for the researcher interested in utilizing multivariate statistics to pre-post data. By finding the linear combination that maximizes differences in the groups, the t-statistic can be computed for correlated samples. (Author)

Data from 2-, 3-, 6-, and 7-point rating scales were analyzed to determine whether scale length affected response patterns. Results indicate that data configurations are relatively invariant with changes in number of scale points. (Author)

Examines the application of the Rasch simple logistic model to analogy test items. (RC)

A scale was prepared for measuring the effects of indirect suggestion upon perception. Three categories were included: 1) distorting the interpretation of presented stimuli, 2) inducing sense-impressions in the absence of adequate stimuli, and 3) producing insensitivity to stimuli that are objectively present. (Author/RC)

Describes some of the situations in which a psychologist is likely to violate the assumption of independent errors. A Monte-Carlo study of the effects of this violation is then described. (Author/RC)

Two major purposes were to (1) appraise the extent to which relatively naive item writers can produce valid personality scales, and (2) compare these scales with scales derived from other strategies, particularly those employing empirical methods using an external criterion. (Author/RC)

Presents a series of analyses of Jackson's Personality Research Form items and scales to determine the apparent effects of the use of the differential validity index on more traditional item psychometric indices which have been used to reduce the confounding of trait scales and social desirability. (Author/RC)