Tree Models of Similarity and Association, Issue 112Clustering and tree models are being widely used in the social and biological sciences to analyze similarity relations. This volume describes how matrices of similarities or associations among entities can be modelled using trees, and explains some of the issues that arise in performing such analyses and interpreting the results correctly. James E Corter distinguishes ultrametric trees from additive trees and discusses how specific aspects of each type of tree can be interpreted through the use of applications as examples. He concludes with a discussion of when tree models might be preferable to spatial geometric models. |
Common terms and phrases
additive inequality agglomerative Aldenderfer algorithms for fitting analysis applications Arabie arc lengths arson average-link clustering b₁ badness-of-fit cluster models column combinatoric common features computing corresponding Corter criterion data dissimilarities data matrix data set dendrogram DeSarbo estimated example fitting additive trees fitting trees fitting ultrametric trees hierarchical clustering internal node interpreted leaf arcs least squares mathematical programming measure methods for fitting minimal spanning tree models of proximity multidimensional scaling multiple regression neighbor score optimal pair of objects parameters partition path-length distances principal components analysis proximity data proximity matrix quadruples of objects representing researcher resulting rooted additive tree satisfy the additive satisfy the ultrametric Sattath & Tversky Sattath and Tversky sets of objects shoplifting singular tree Sneath & Sokal Social Sciences Soete spatial model SPSS statistical SYSTAT tree graph tree models tree of Figure tree solution tree structure tree-fitting triangle inequality ultrametric inequality unrooted variables weight
Popular passages
Page 62 - Fitting of hierarchical tree structure (HTS) models, mixtures of HTS models, and hybrid models, via mathematical 6l programming and alternating least squares.
Page 62 - Ultrametric tree representations of incomplete dissimilarity data." Journal of Classification, I, 235-242. De SOETE, G. (i986) "Optimal variable weighting for ultrametric and additive tree clustering.
Page 64 - PATHFINDER Associative Networks: Studies in Knowledge Organization. Norwood, NJ: Ablex. SCOTT, J. (i99i ) Social Network Analysis. Newbury Park, CA: Sage. SHEPARD, RN (i980) "Multidimensional scaling, tree-fitting, and clustering.