Factor analysis in several populations, covariance structure models, three-mode factor analysis, structural equations systems with measurement model, and analysis of covariance with measurement model are all shown to be specializations of a general moment structure model. Some new structured linear models are also described. (Author/CTM)

Dunnett's procedure for comparing K-1 treatments with a control is discussed within the context of three nonparametric models: those of Kruskal-Wallis, Friedman, and Cochran. (Author/MH)

Two techniques for interpretation of fitted log-linear models in contingency table analysis are discussed. The use of odds ratios as opposed to direct interpretation of the fitted model is argued for. (Author/JKS)

A theory and a procedure are presented for estimating a domain parameter and item parameters for test items in a homogeneous domain, such that the combined domain and item parameters account for observed proportions right for each item in a test. (CTM)

A multivariate model was constructed to test and compare sets of social location and consciousness factors explaining political behavior among two random samples of college and noncollege youth. The form of Mannheim's generation unit model provided a useful tool for comparing youth groups within the same generation; the contents await replication…

Uses time-series analysis to study effects of changes in tuition and other factors on enrollment at U.S. private colleges and universities. Argues that enrollment demand function should be expressed in a dynamic model. Actual enrollment adjusts to the desired enrollment very slowly; tuition and other related costs significantly affect enrollment…

Uses 1995 Italian household income and wealth survey to measure individual absolute risk aversion of 1,583 married Italian male household heads. Uses this measure as an instrument for attained education in a standard-log earnings equation. Finds that the IV estimate of the marginal return to schooling is much higher than the ordinary least squares…

A guide to the use of microcomputer statistical analysis packages for loglinear analysis describes the application of one popular package to a straightforward problem and critically surveys features available in four of the leading packages. Survey findings and suggestions for further development are included. (Author/MSE)

Examines structural features of grade point averages (GPAs) and offers examples showing that GPAs cannot consistently determine class rank since class rank is sometimes permuted with arbitrary change of scale. Notes relativistic efforts to resolve inconsistencies are insufficient. Discusses the function of GPAs as predictors of academic…

The question of how to estimate school and teacher contributions to student learning is fundamental to educational policy and practice, and the three thoughtful articles in this issue represent a major advance. The current level of public confusion about these issues is so severe and the consequences for schooling so great that it is a big relief…

For much of the twentieth century, Markov theory and Markov processes have been widely accepted as valid ways to view statistical variables and parameters. In the complex realm of online searching, where researchers are always seeking the route to the best search strategies and the most powerful query terms and sequences, Markov process analysis…

Fisher's information measure for the item difficulty parameter in the Rasch model and its marginal and conditional formulations are investigated. It is shown that expected item information in the unconditional model equals information in the marginal model, provided the assumption of sampling examinees from an ability distribution is made. For the…

A procedure for the sequential optimization of the calibration of an item bank is given. The procedure is based on an empirical Bayes approach to a reformulation of the Rasch model as a model for paired comparisons between the difficulties of test items in which ties are allowed to occur. First, it is indicated how a paired-comparisons design…

In an analysis of multitrait-multimethod matrices the criteria for discriminant validity are shown to include a "structure" criterion as an invariance of traits structure to methods. The criterion is meant to fit data to an additive model with traits and methods but not interaction terms. The importance of the structure criterion and the…

The Pearson and likelihood ratio statistics are frequently used for assessing the absolute fit of probability models. Researchers are often interested in comparing fits provided by different models which may have a subsuming or non-subsuming relation. A subsuming relation exists when the parameters of the reduced model form a subset of those…