There are difficulties in expressing effect sizes on a common metric when some studies use transformed scales to express group differences, or use factorial designs or covariance adjustments to obtain a reduced error term. A common metric on which effect sizes may be standardized is described. (Author/RL)

Latent trait models provide a new scale for reporting educational and psychological measurements. Characteristics, interpretations, and uses of these scales are considered. (Author/RL)

Classical queuing theories and their accompanying service facilities totally disregard the human factors in the name of efficiency. As library managers we need to be more responsive to human needs in the design of service points and make every effort to minimize queuing and queue frustration. Five references are listed. (Author/RAA)

Children, 9-11 years old, solved subtraction problems in the form of M-N=..., then gave a verbal report on the thought processes used, analysis of which utilized a model based on analyses of reaction times, and resulted in a more detailed process model. (AN)

Describes a simulation model that examines the relationship of dropout behavior and re-entry flows in a local school system to changes in local socioeconomic factors, school-related conditions, and aspects of labor market participation. Assesses the policy implications for affecting these flows at the local board level. (Author/IRT)

An alternative to the uniform probability distribution model for ordinal data is considered. Implications for statistics and for test theory are discussed. (JKS)

Money models that can be used in a group-instruction mode and a shorthand notation that allows students to demonstrate their ability to count out change by a written procedure are described and discussed. (MK)

Factorial modeling is justified as a method for analyzing correlations in support of causal inference. The method is illustrated and compared to path analysis, LISREL-type analysis, canonical correlation, and commonality analysis. Predictions of impacts of policy manipulations are demonstrated. (Author/CP)

Staddon and Motheral derived a mathematical model of responding in concurrent variable-interval--variable-interval schedules. Their derivation ignores a fundamental aspect of the concurrent schedule contingency. A reinforcer can occur following two consecutive responses on the same schedule or following a switch between the two schedules.…

Heyman's major criticism (TM 504 810) of Staddon and Motheral's reinforcement maximization model is that it does not consider "local" and "interchangeover" interresponse times separately. We show that this separation may not be necessary. Heyman's apparent gain in comprehensiveness may not be worth the added complexity.…

In the study reported here a cost model of facility usage was constructed to assess the financial impact of alternative facility usage policies. Results of the study indicate that the financial benefits that accrue from increased facility utilization would likely be more than offset by increased costs. (Author)

This survey of current work on data base systems is divided into three main sectors: data models, data languages, and support for data base operations, including hardware for content addressing, data base machines, and software techniques for optimizing and evaluating group expressions. A 203-item bibliography is provided. (Author/JD)

An example demonstrates that Joreskog's suggested sufficient conditions for identifying unknown parameters in a confirmatory factor analytic model with correlated factors are not sufficient. Sufficient conditions are presented. (Author/JKS)

Assuming that subject responses rank order stimuli by preference, statistical methods are presented for testing the hypothesis that responses conform to a unidimensional, qualitative unfolding model and to an a priori stimulus ordering. The model is suitable for the analysis of structure in attitude responses, preference data, and developmental…

The Bayesian approach to setting passing points on credentialing examinations in the health fields is considered in the context of the Normal model, and examples are given to demonstrate the procedure. An application to a credentialing examination, to determine a rational passing point, is presented. (Author/MH)