The coefficient of precision type of reliability originally defined for scalar variables is generalized to vector variables and named vector reliability. The new coefficient ranges from zero to one. Additional basic properties of vector reliability are derived. Vector information is defined as a simple function of vector reliability. A number of…

To provide a further test of the paired-associate analogy to retroactive inhibition in free recall, this experiment investigated the effect of presenting both original learning (OL) and interpolated learning (IL) in either blocked category (B) or random (R) fashion. IL-OL Similar (S), IL-OL Different (D), and control (C) conditions were included.…

The applicability of the Analysis of Variance, ANOVA, procedures to the analysis of dichotomous repeated measure data is described. The design models for which data were simulated in this investigation were chosen to represent simple cases of two experimental situations: situation one, in which subjects' responses to a single randomly selected set…

TO DEVELOP A BETTER MATHEMATICAL BASIS FOR FACTOR ANALYSIS, A MATHEMATICAL APPROACH WAS FORMULATED FOR FIXING COMMUNALITIES AND THEIR COMPLEMENTS, UNIQUENESSES, AS WELL. WHILE THE INVESTIGATOR WAS UNABLE TO PROVE THAT MINIMUM-TRACE CRITERIA FIX COMMUNALITIES UNIQUELY, A SET OF IDENTITIES AND INEQUALITIES WAS LOCATED AMONG THE COMMUNALITIES AND,…

THE NATURE OF THE INTERACTING RELATIONSHIP BETWEEN PERSONALITY CHARACTERISTICS OF COLLEGE STUDENTS AND ENVIRONMENTAL CHARACTERISTICS OF THE INSTITUTIONS THEY ATTEND WAS EXPLORED. STUDENT PERSONALITY WAS MEASURED FOR SAMPLES FROM 55 COLLEGES AND UNIVERSITIES BY THE ACTIVITIES INDEX, AN INSTRUMENT DESIGNED TO MEASURE PERSONALITY NEEDS. PRESS,…

The stability of the structure underlying a fourteen item rating scale (the In-Training Evaluation Report) when completed on two different groups of medical candidates was investigated at the Royal College of Physicians and Surgeons of Canada. In addition the relationship between the rating scale score and scores on other measures such as multiple…

A general statistical model for the multivariate analysis of mean and covariance structures is described. Matrix calculus is used to develop the statistical aspects of one new special case in detail. This special case separates the confounding of principal components and factor analysis. (DEP)

A procedure for estimating the reliability of a factorially complex composite is considered. An application of its use with Scholastic Aptitude Test data is provided. (Author/JKS)

The Cartesian theory of dimensionality (defined in terms of geometric distances between points in the test space) and Leibnitzian theory (defined in terms of order-generative connected, transitive, and asymmetric relations) are contrasted in terms of the difference between a factor analysis and an order analysis of the same data. (Author/CTM)

Two sets of five items each from the Law School Admission Test were analyzed by two methods of factor analysis, and by the Krus-Bart ordering theoretic method of multidimensional scaling. The results indicated a conceptual gap between latent trait theoretic procedures and order theoretic procedures. (Author/CTM)

This article discusses two basic issues in the interpretation of factorial investigations (descriptive vs causal inferences and group vs individual characteristics); updates previously published reviews of factor-analytic studies in rehabilitation under five categories (counselor, client, instruments, attitudes, and environments); and outlines…

Using 144 high school physics classes as units of analysis, class means on a battery of 57 variables were factored in three different factor sets. Each set included three main factors which could be identified roughly as achievement, affect, and group structure. Results gave further credibility to Bales' work. (Author/KR)

Satisfaction of expectations (quality of care) is more important in determining willingness to return than are race, sex of provider, or care setting. (Author)

Examines the Personal Health Survey methodology and suggests that in studying the factorial composition of physical and mental health complaints in limited populations, the data provides normative information "only" for the samples tested on one occasion. States further that it would require large-scale normative studies to make any…

Assessed the psychometric structure of a neuropsychological test battery in order to assist in understanding the predictive and descriptive components in the diagnosis of organic brain disturbance. The methods chosen were both linear and nonlinear, factor analysis and hierarchical cluster analysis. (Author)