Relations on a finite set V are viewed as weighted graphs. Using the language of graph theory, two methods of partitioning V are examined: selecting threshold values and applying them to a maximal weighted spanning forest, and using a parametric linear program to obtain a most adhesive partition. (Author/EM)

The purpose of this paper is to demonstrate in detail how the Empirical Bayes (EB) statistical estimation strategy can be applied to an important class of educational research contexts. EB methods are tailored specifically to the analysis of data with a hierarchical structure. For instance, investigators may be interested in discovering how…

Lord's Paradox is analyzed in terms of a simple mathematical model for causal inference. The resolution of Lord's Paradox from this perspective has two aspects. First, the descriptive, non-causal conclusions of the two hypothetical statisticians are both correct. They appear contradictory only because they describe quite different aspects of the…

Several steps are taken to develop methods for analyzing systems that involve probabilistic causation. The basic ideas and distinctions are illustrated for systems with dichotomous variables. It is shown that these basic ideas have analogous counterparts in causal systems with continuous variables. By using a generalized conditional probability…

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)

The approach of J. D. Sneed is used to argue for a distinction between theoretical and nontheoretical (or empirical) entities. Attention is directed toward this approach as an important facility for looking at statistics and for constructing a framework for the correct use of statistical theory in information retrieval experiments. (MBR)

Proposes a new definition of the nuclear zone of a Bradford or Leimkuhler curve. The mathematical rationale is outlined, and examples of the application of this technique to citation analysis are given. (15 references) (CLB)

Provides an introduction to loglinear analysis of cross-classification tables, including tables with nominal and ordinal variables. Compares the chi-square test of independence with the loglinear model of independence. Reviews the advantages and overall strategy of loglinear modeling. Each model discussed is applied to data from the developmental…

The Generalized Inverse Gaussian-Poisson Distribution is suggested as an all-embracing mathematical model for bibliometric frequency distributions. Twelve examples are given which show that the new model cannot be rejected by virtue of an objective chi-squared test. A mathematical appendix and 20 references are included. (Author/EJS)

Methodological implications of a person-oriented, holistic-interactionistic perspective in research on individual development are outlined, desirable properties of a mathematical model of a phenomenon are discussed, and selected methods for carrying out person-oriented research are briefly overviewed. These methods are: (1) the classificatory…

During the past 15 years, considerable attention has been given to a conspicuous longitudinal change in grading patterns in higher education. Commonly referred to as "grade inflation," the phenomenon has been perceived by some as seriously weakening the meaning of grades but by others as reflecting a positive tendency for students to…

The overidentification of structural equation models with latent variables is discussed. The use of two- and three-indicator models is not recommended since such models do not allow a testing of the crucial assumption of unidimensionality among indicators in most cases. Models with four or more indicators may be more sensitive to departures from…

The purpose of this paper is to demonstrate how multiple linear regression provides a viable statistical methodology for dealing with meta-analysis in general, and specifically with the issues of nonindependence and design complexity, such as multiple treatments. Since the F-test and t-test are special cases of the general linear model,…

Describes operations research as an important management tool that can aid library managers in effectively using available resources and as a set of analytical tools that can enable researchers to better understand library and information services. Early history, definition, models, applications to libraries, and impact are noted. Twenty-five…

A confirmatory factor analysis was used to determine the respective viability of factor structure models for the Wechsler Adult Intelligence Scale-Revised (WAIS-R) standardization data. The traditional verbal-performance split was compared to an alternative model proposed by Gutkin, Reynolds and Galvin. The confirmatory analysis indicated that the…