Presents a new procedure for comparing the results of linear and equipercentile equating methods. The new method calculates the expected degree of efficiency in equating that can be achieved by linear equating based on the moments of the two relevant distributions. (RB)

The threshold utility model for culture-fair selection is defined for both quota-free and for restricted selection. In addition a full Bayesian solution based on posterior predictive distributions is provided. Mathematical derivations and an example are provided. (JKS)

This comment is intended to complement points made by Freedman in his critique of the path analysis method. The role of statistical analysis in social sciences is also discussed. (RB)

Two multinomial random sociometric voting models are presented to study the critical number of votes that can occur under peer voting schemes. Empirical evidence for the convergence of the models is presented to simplify calculating critical values of sociometric frequencies attributed in classroom groups which vary in size. (Author/BW)

Manifest discrete time and latent Markov chain models are described, and the results given by each are compared for the re-analysis of a three-wave table of repeated behavior ratings of children. More recent developments in latent discrete time Markov chain modeling address the problems of the table more efficiently. (SLD)

Explains two methods of systems analysis: the Fix-Point (FP) and the Partial Least Squares (PLS). Argues against Freedman's rejection of the structural assumptions of path analysis models. (RB)

Freedman responds to a series of articles commenting on his critique of the path analysis model. The focus of this rejoinder is the assumptions made by researchers who use the path analysis method, particularly the assumption that the equations in path analysis are structural. (RB)

Two alternatives to the problems of conducting planned and post hoc comparisons in tests of concordance and discordance for G groups of judges are examined. The two models are illustrated using existing data. (Author/JKS)

Two forms, pure-rank and mixed-rank, of a nonparametric, general, linear model-based statistic that can be used to test several hypotheses are presented. A Monte Carlo study was used to investigate the distributional properties of these forms, and their use is discussed. (SLD)

Response to Freedman's critique of path analysis discusses appropriate ways to represent social processes in numerical form and the use of path analysis to achieve that goal. Discusses two main issues: the selection of variables and whether multiple regression can be used to model social processes. (RB)

Discusses the theoretical aspects of structural modeling rather than its applications. Considers the basic hypothesis in structural modeling and concludes that it can be an effective tool in some research contexts, though not all. (RB)

Suggests that improving the data collected for a study will lead to the development of better models to analyze that data. Also urges researchers to have a more critical attitude toward the literal interpretation of test results. (RB)

In the case of dichotomous decisions, the total set of all assumptions/specifications for which the decision would have been the same is the robustness region. Inspection of this (data-dependent) region is a form of sensitivity analysis which may lead to improved decision making. (Author/BW)

Simple Markov models are fitted to a small sample of longitudinal categorical data of teachers' ratings of children's classroom behavior. Although the data consist only of observations at five occasions, it was possible, after dividing the data into two groups, to fit plausible models in continuous time. (Author/BW)

Data evolving from processes which are developmental or hierarchical in nature are often analyzed by using latent class or latent structure models. A procedure for estimating such models when the model is not "identifiable" is presented. (JKS)