Office of Survey Methods Research

Abstract

Patrick Bobbitt (2003) "A Graphical Method for Assessing the Results of Fuzzy Clustering."

In one sense, statistics is practice of summarizing data by reducing the dimensionality of a data set in a sensible way. One way in which the dimensionality of a data set can be reduced is to classify the n items in a dataset into k clusters. One such method of classification is known as the k-means clustering algorithm. In this algorithm the statistician uses a measure of distance between the items to define items in a dataset as similar, and then classifies that item as having membership to one of k clusters.

Last Modified Date: July 19, 2008

Recommend this page using: