INFORMATION MEASURE FOR SINGLE LINK CLASSIFICATION.

Abstract

The information measure is an objective measure of the quality of a classification and results from an information transmission view of the classification problem. So far information measures have only been derived for the case where an explicit assumption is made about the form of the distribution of attribute values within a class. One important method which involves no such explicit assumptions is single link, In this paper a new information measure is derived which is optimized by classifications produced by the single link method. By investigating the properties of this information measure it is possible to gain more insight into the single line method and also to determine the type of problem to which it best applies.