Data Architecture

13. Concepts of Clustering, Indexing, and Structures

Cluster Analysis

Cluster analysis is a generic term applied to a large number of varied processes used in the classification of objects. For the last 30 years, cluster analysis has been used in a large number of fields. For the purposes of this discussion, we will restrict interaction with clustering primarily to data. Although it is on these principles that some of the foundation of relational theory was based, the concept of clusters is pervasive through all types of data structure theories. We will have a generic discussion on clusters and segue into how this applies to data.

What Is a Cluster?

Everitt (1980) studied the definitions of a cluster and found that the most common feature of the ...