Measuring Resemblance in Sequence Data: An Optimal Matching Analysis of Musicians' Careers

Abstract

This article introduces a method that measures resemblance between sequences using a simple metric based on the insertions, deletions, and substitutions required to transform one sequence into another. The method, called optimal matching, is widely used in natural science. The article reviews the literature on sequence analysis, then discusses the optimal matching algorithm in some detail. Applying this technique to a data set detailing careers of musicians active in Germany in the 18th century demonstrates the practical steps involved in the application of the technique and develops a set of typical careers that successfully categorize most of the actual careers studied by the authors.