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)

One purpose for combining research studies is to estimate a population treatment effect. The internal validity of a model for how effect size estimates should be computed and combined will hinge upon the homogeneity of the effect size variation. Effect size variation may be assessed in the form of a summary fit statistic, and a direct…

The meta-analysis investigated the effects on achievement of type of graphing paper employed in displaying student performance data collected over time based on 15 controlled studies with 16 effect sizes. No significant differences in student achievement were found between studies using six-cycle and studies using equal interval paper graphing…

After discussion of the equivalency of the information laws of Bradford, Leimkuhler, Lotka, and Mandelbrot, aberrations from Leimkuhler's law (including "Groos droop" as encountered in practice) are studied. Other aberrations of Leimkuhler's law are explained, starting from generalization of verbal formulation of Bradford's Law. (18…

Sixty-one examiners provided a rating of whether a significant change in performance of handicapped individuals occurred across the baseline and treatment phases of six graphs of hypothetical data from single-subject designs. Results revealed considerable interrater disagreement on four graphs, especially those involving change in variability or…

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)

This article adopts "citation approach" to distinguish interdisciplinary or multidisciplinary research (IDR) from monodisciplinary research and begins to descrie how IDR differs from other research. Ten-year citation histories were constructed for sample of 1981 "citation classics" (over-cited articles) and examined for…

Techniques of exploratory data analysis (EDA) were used to decompose data tables portraying performance of ethnic groups on the Scholastic Aptitude Test. These analyses indicate the size and structure of differences in performance among groups studied, nature of changes across time, and interactions between group membership and time. (Author/DWH)

Introduces Q-analysis, a methodology for investigating a wide range of structural phenomena that defines structures in terms of relations between members of sets and reveals their salient features by using techniques of algebraic topology. Applications relevant to librarianship and information science are reviewed and present limitations…

Examination of how far research work on the design of printed text can inform research on the design of electronic text centers on three areas: the layout of instructional text, the role of typographic cueing, and the presentation of graphic materials. Future research needs are discussed, and 101 references are provided. (LRW)

Utilizing 11 years of University of Saskatchewan circulation transactions, it is shown that P. M. Morse's Markov model of book use fits approximately 99 percent of data for whole collection and for three subject areas; contrary to his assumptions, one of the model's parameters is time dependent. Thirteen references are included. (EJS)

The pre-math computer program for preschool children that is described is divided into subprograms representing different basic numerical concepts--discrimination, recognition, and recall--and presents research design used to test the program's effectiveness with Head Start preschool children. Results indicate the program was ineffective…

This research illustrates how statistical analysis of data was presented by the plaintiff's attorneys as evidence in litigation involving sexual and racial discrimination in the case Green v. City of Gadsden. Bar graphs depict the sexual and racial compositions of (1) members of the Gadsden Police Department (GPD), (2) members of the GPD in…

A subset of Statistical Process Control (SPC) methodology known as Control Charting is introduced. SPC methodology is a collection of graphical and inferential statistics techniques used to study the progress of phenomena over time. The types of control charts covered are the null X (mean), R (Range), X (individual observations), MR (moving…

Discusses reliability and validity of continual response measurement (CRM), a computer-based measurement technique, and its use in social science research. Highlights include the importance of criterion-referencing the data, guidelines for designing studies using CRM, examples typifying their deductive and inductive functions, and a discussion of…