Market Structure Analysis: Hierarchical Clustering of Products Based on Substitution-in-Use

Abstract

In this paper, product usage data, employing a substitution-in-use criterion, are analyzed and shown to yield managerially useful product-market structures for financial services. These structures are identified through a form of hierarchical clustering which is different from traditional clustering routines in that it focuses on the explained or accounted for variance in the categorization of objects, thereby reducing groupings due to chance covariation.