Record Display for the EPA National Library Catalog

RECORD NUMBER: 6 OF 165

OLS Field Name OLS Field Data
Main Title Application of Cluster Analysis to Growing Season Precipitation Data in North America East of the Rockies.
Author Gong, X. ; Richman, M. B. ;
CORP Author Oklahoma Univ., Norman. Cooperative Inst. for Mesoscale Meteorological Studies.;Environmental Protection Agency, Research Triangle Park, NC. National Exposure Research Lab.
Publisher cApr 95
Year Published 1995
Report Number EPA-R-816318-02-0; EPA/600/A-96/089;
Stock Number PB97-122774
Additional Subjects Cluster analysis ; Precipitation(Meteorology) ; Geophysics ; Algorithms ; Monte Carlo Method ; Reprints ;
Holdings
Library Call Number Additional Info Location Last
Modified
Checkout
Status
NTIS  PB97-122774 Most EPA libraries have a fiche copy filed under the call number shown. Check with individual libraries about paper copy. NTIS 02/22/1997
Collation 46p
Abstract
Cluster analysis (CA) has been applied to geophysical research for over two decades although its popularity has increased dramatically over the past few years. To date, systematic methodological reviews have not appeared in geophysical literature. In this paper, after a review of a large number of applications on cluster analysis, an intercomparison of various cluster techniques was carried out on a well-studied dataset (7-day precipitation data from 1949 to 1987 in central and eastern North America). The cluster methods tested were single linkage, complete linkage, average linkage between groups, average linkage within a new group, Ward's method, k means, the nucleated agglomerative method, and the rotated principal component analysis. Three different dissimilarity measure (Euclidean distance, inverse correlation, and theta angle) and three initial partition methods were also tested on the hierarchical and nonhierarchical methods, respectively. Twenty-two of the 23 cluster algorithms yielded natural grouping solutions. Monte Carlo simulations were undertaken to examine the reliability of the cluster solutions. This was done by bootstrap resampling from the full dataset with four different sample sizes, then testing significance by the t test and the minimum significant difference test.