More than one correlation coefficient can be computed between two variables when the data can be organized into subsets determined by one of more grouping factors. Implications of this fact are discussed when the variables are items and the correlations are being computed for purposes of scale development. (Author/

Discusses the issue of centralization or decentralization of academic library collections, and describes a statistical analysis of book circulation at the University of Southwestern Louisiana that yielded subject area clusters as a compromise solution to the problem. Applications of the cluster model for all types of library catalogs are…

Describes multidimensional scaling and cluster analysis and the type of problems they can help solve. Cites major literature sources concerning their use. Reviews applications of these methods in rehabilitation research. Discusses possible advantages of nonmetric data-reduction techniques over metric approaches, such as factor analysis. (Author)

Reviews visualization techniques for scientific disciplines and information retrieval and classification. Highlights include historical background of scientometrics, bibliometrics, and citation analysis; map generation; process flow of visualizing knowledge domains; measures and similarity calculations; vector space model; factor analysis;…

Uses multidimensional scaling and clustering analysis of the co-citation patterns of 58 authors to explore the intellectual organization of population genetics and related specialties. Concludes that co-cited author mapping, with the author as the unit of analysis, is likely to complement studies of informal communication networks. (SR)