Two stage multiple-comparison procedures give an exact solution to problems of power and Type I errors, but require equal sample sizes in the first stage. This paper suggests a method of evaluating the experimentwise Type I error probability when the first stage has unequal sample sizes. (Author/BW)

Examines relationships among the parameters of the Zipf size-frequency distribution as well as its sampling properties. Highlights include its importance in bibliometrics, tables for the sampling distribution of the maximal value of a finite Zipf distribution, and an approximation formula for confidence intervals. (Author/LRW)

Reparameterization is used to find the maximum likelihood estimates of parameters in a multivariate model having some component variable observable only in polychotomous form. Maximum likelihood estimates are found by a Fletcher Powell algorithm. In addition, the partition maximum likelihood method is proposed and illustrated. (Author/GDC)

This exploratory study determined whether a mathematical model of mastery learning provided a good fit for achievement data obtained from student progress in an introductory, college-level astronomy course for nonmajors. Results provide positive but not compelling evidence that the model of mastery learning is correct. (JN)

This three-part article introduces a population dynamics model of an information processing system. The first part describes the general model and defines the terms used, the second describes the functional relationships between components, and the third explores the hypothesized emergence of increasingly complex, hierarchical information systems.…

Modeling the process by which participants are selected into groups, rather than adjusting for preexisting group differences, provides the basis for several new approaches to the analysis of data from nonrandomized studies. Econometric approaches, the propensity scores approach, and the relative assignment variable approach to the modeling of…

Argues that library book circulation is a binomial rather than a Poisson process, and that individual book popularities are continuous beta distributions. Three examples demonstrate the superiority of beta over negative binomial distribution, and it is suggested that a bivariate-binomial process would be helpful in predicting future book…

This article organizes models for categorical item response data into three distinct classes. "Difference models" are appropriate for ordered responses, "divide-by-total" models for either ordered or nominal responses, and "left-side added" models for multiple-choice responses with guessing. Details of the taxonomy…

A computational model of the neural substrates of elementary associate learning is developed. It is used to demonstrate that several higher order features of classical conditioning could be elaborations of the known cellular mechanisms for simple associative learning. (Author/LMO)

The most familiar models of item response theory are defined at the level of individual subjects. It is possible, however, to define such models for groups of subjects. This paper discusses group-level item response models, their uses, and their relationships to subject-level models. (Author/JKS)

A structural equation model is proposed with a generalized measurement part, allowing for dichotomous and ordered categorical variables (indicators) in addition to continuous ones. A computationally feasible three-stage estimator is proposed for any combination of observed variable types. Two multiple-indicator modeling examples are given.…

Presents a general mathematical framework for information retrieval, in which query evaluation is seen as a mapping from the free term algebra built by query descriptors and weights to the semantic algebra of evaluation value. Competing mathematical models that try to describe how retrieval systems behave are reviewed. (Author/MBR)

A constrained quadratic spline is proposed as an estimator of the hazard function of a random variable. A maximum penalized likelihood procedure is used to fit the estimator to a sample of psychological response times. (Author/LMO)

Presents a procedure for calculating the compass direction and velocity of present plate motions at any geographical point of interest. Includes a table of the relative and geographic motion of the 11 largest plates and a flow chart for determining their present motion. Also offers suggestions for classroom instruction. (ML)

A method requiring minimal computational effort is presented for transforming ordered residuals for purposes of testing the correctness of a regression model. The method maintains the same logical ordering in the transformed residuals as that of the original residuals and is suitable for either correlated or uncorrelated data. (Author/BS)