Describes the use of loglinear statistical models in the field of informetrics, especially for the analysis of information systems. A detailed example is given of developing a model based on loglinear analysis to determine book acquisition patterns in libraries, including mathematical considerations and algorithms. (19 references) (LRW)

Two causal models are presented to describe influences on the performance of students with learning disabilities. The first model associates reading and math with three domains: neuropsychological, linguistic, and social-behavioral. The second model involved relationships among selected individual variables and suggests that learning disability is…

A method is presented that eliminates some interpretational limitations arising from assumptions implicit in the use of arbitrary rules of thumb to interpret exploratory factor analytic results. The bootstrap method is presented as a way of approximating sampling distributions of estimated factor loadings. Simulated datasets illustrate the…

A mathematical formula is introduced for the effect of integrating data. A method is then derived to eliminate the effect from correlations of variables, including mean composites, thus allowing for a clustering algorithm that requires allocation of variables according to the magnitude of their correlations. Examples illustrate the procedure. (SLD)

The Sixteen Personality Factor Inventory (16PF) was examined concerning recent methodological and substantive developments: restricted (confirmatory) factor analysis, and the five-factor model of personality as operationalized in the NEO-Personality Inventory. Two studies with 645 college students show that the 16PF remains robust in light of…

A method is outlined for analysis of the shape of an individual profile of scores on a standardized test battery. The method uses a simultaneous test procedure allowing for an overall test of profile flatness, with follow-up tests on all contrasts of interest. (SLD)

A method is presented for determining the optimal number of conditions to use in measurement designs when resource constraints are imposed. The method is illustrated using a multivariate two-facet design, and extensions to other designs are discussed. (SLD)

A statistical test of the knowledge or random guessing model is presented. A version of the model is introduced in which it is assumed that alternatives can be ordered according to a Guttman scale. Three examples illustrate its application to data from a total of 590 college students. (Author/SLD)

F. Samejima's approximation for the bias function for the maximum likelihood estimate of the latent trait in the general case where item responses are discrete is explored. Observations are made about the behavior of this bias function for the dichotomous response level in general. Empirical examples are given. (SLD)

A probabilistic choice model, based on L. L. Thurstone's Law of Comparative Judgment Case V, is developed for paired comparisons data about psychological stimuli. The model assumes that each stimulus is measured on a small number of physical variables. An algorithm for estimating parameters is illustrated with real data. (SLD)

Scoring of response vectors to give maximum test-retest correlation is investigated. A general method is given for finding the best scores, deriving them for the normal factor model, and showing that for a standard model for binary response it is easy to approximate the best scores. (SLD)

Polynomial algorithms are presented that are used to solve selected problems in test theory, and computational results from sample problems with several hundred decision variables are provided that demonstrate the benefits of these algorithms. The algorithms are based on optimization theory in networks (graphs). (SLD)

A connectionist model of argument strength that applies to categorical arguments involving natural categories and predicates about which subjects have few prior beliefs is proposed. This feature-based model was tested in argument strength rating studies with 34 undergraduates, and its validity is discussed. (SLD)

Principal component, image component, three types of factor score estimates, and one scale score method were compared over different levels of variables, saturations, sample sizes, variable to component ratios, and pattern rotations. There were virtually no overall differences among methods, with the average correlation between matched scores…

The problem of measuring impacts of employment and training programs when workers not receiving services are affected by the program is explored, using a reemployment bonus program as an example. The conventional measures of bonus impacts may significantly overestimate the net impact of the bonus offer. (SLD)