A Hybrid Clustering Method for Identifying High-Density Clusters

Wong, M. Anthony

doi:10.2307/2287316

Cited by 33 publications

(17 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The SASS System provides six kinds of programs for cluster analyses; i. e., average linkage (Sokal and Michener 1958), centroid hierarchical (Sokal and Michener 1958), density linkage (Wong 1982, Wong andLane 1983), single linkage (Florek et a/. 1951, McQuitty 1957, McQuitty 1966, Sneath 1957), two-stage density, and Ward's minimum variance (Ward 1963) cluster analyses.…”

Section: Discussionmentioning

confidence: 99%

Phenetics in Tree Peony Species from China by Flower Pigment Cluster Analysis

et al. 2001

View full text Add to dashboard Cite

Petal pigment compositions were used as markers to study the phenetic relationships among seven wild tree peony species of Paeonia section Moutan DC. (fifteen accessions) from China. As the pigment markers, five anthocyanins together with three flavone and three flavonol aglycones were used. Principal component analysis (PCA) provided five eigenvectors from nineteen pigment patterns, in which peonidin and cyanidin as well as the types of glycosides greatly influenced the first factor, Z1. The Euclidean distances of standardized values obtained by eigenvector matrices with five factors (Zl to Z5) produced a dendrogram in Ward's minimum variance cluster analysis, which showed good agreement with a classification based on the morphological characteristics of two subsections Vaginatae F.C. Stern and Delavayanae F.C. Stern. The results obtained by PCA and clustering qualify a chemical classification of section Moutan using secondary metabolites, specifically flower pigments, as taxonomic markers.

show abstract

Section: Discussionmentioning

confidence: 99%

Phenetics in Tree Peony Species from China by Flower Pigment Cluster Analysis

et al. 2001

View full text Add to dashboard Cite

show abstract

“…130-145], based on [54]) is carried out on eight MCA first principal axes, accounting for a significant proportion of the inertia contained in the data table. This process starts by choosing a partition in a number of clusters with random initial centres and then updating those centres calculating the centroids of the groups of individuals nearest to the centres (K-means algorithm); the process is repeated until the clusters are stable.…”

Section: Mca Of Categorical Variables and Clusteringmentioning

confidence: 99%

Knowledge extraction from a large on-line survey: a case study for a higher education corporate marketing

Fernandez-Aguirre

Landaluce-Calvo

Martín-Arroyuelos

et al. 2011

Journal of Applied Statistics

View full text Add to dashboard Cite

For a higher education public institution, young in relative terms, featuring local competition with another private and both long-established and reputed one, it is of great importance to become a reference university institution to be better known and felt with identification in the society it belongs to and ultimately to reach a good position within the European Higher Education Area. These considerations have made the university governors setting up the objective of achieving an adequate management of the university institutional brand focused on its logo and on image promotion, leading to the establishment of a university shop as it is considered a highly adequate instrument for such promotion. In this context, an on-line survey is launched on three different kinds of members of the institution, resulting in a large data sample. Different kinds of variables are analysed through appropriate exploratory multivariate techniques (symmetrical methods) and regression-related techniques (non-symmetrical methods). An advocacy for such combination is given as a conclusion. The application of statistical techniques of data and text mining provides us with empirical insights about the institution members' perceptions and helps us to extract some facts valuable to establish policies that would improve the corporate identity and the success of the corporate shop.

show abstract

“…The former are implemented by sequentially merging or dividing groups of observations into proper clusters, while the latter attempt to group the observations into a predetermined number of clusters. The hierarchical algorithms include single linkage (or nearest neighbor), average linkage (or average distance), centroid linkage, complete linkage (or farthest neighbor), minimum variance method [14], and hybrid method [15], amongst others. The non-hierarchical algorithms include K-means [16], Euclidean cluster analysis [17], and algorithm by Friedman and Rubin [18].…”

Section: Literature Reviewsmentioning

confidence: 99%

Stratified random sampling for estimating billing accuracy in health care systems

Buddhakulsomsiri

Parthanadee

2007

Health Care Manage Sci

View full text Add to dashboard Cite

This paper presents a stratified random sampling plan for estimating accuracy of bill processing performance for the health care bills submitted to third party payers in health care systems. Bill processing accuracy is estimated with two measures: percent accuracy and total dollar accuracy. Difficulties in constructing a sampling plan arise when the population strata structure is unknown, and when the two measures require different sampling schemes. To efficiently utilize sample resource, the sampling plan is designed to effectively estimate both measures from the same sample. The sampling plan features a simple but efficient strata construction method, called rectangular method, and two accuracy estimation methods, one for each measure. The sampling plan is tested on actual populations from an insurance company. Accuracy estimates obtained are then used to compare the rectangular method to other potential clustering methods for strata construction, and compare the accuracy estimation methods to other eligible methods. Computational study results show effectiveness of the proposed sampling plan.

show abstract

A Hybrid Clustering Method for Identifying High-Density Clusters

Cited by 33 publications

References 0 publications

Phenetics in Tree Peony Species from China by Flower Pigment Cluster Analysis

Phenetics in Tree Peony Species from China by Flower Pigment Cluster Analysis

Knowledge extraction from a large on-line survey: a case study for a higher education corporate marketing

Stratified random sampling for estimating billing accuracy in health care systems

Contact Info

Product

Resources

About