Analyzing Sequence Data: Optimal Matching in Management Research

In this article we discuss optimal matching (OM), an invaluable yet underutilized tool in the analysis of sequence data. Initially developed in biology to identify and study patterns in DNA sequences, OM subsequently migrated over to sociology, where it has been used to examine career patterns in life course research. It involves the computation of the number of insertions, deletions, and substitutions of sequence elements that are needed to transform one sequence into another and the costs associated with such transformations. The goal is to identify similarities across sequences, which can then be used for pattern identification. Along with a discussion of the logic underlying OM analysis, we provide an illustration of its use in the examination of careers of deans at U. S. business schools. In addition, we use Monte Carlo simulation to compare OM and cluster analysis and highlight the superiority of OM analysis in the analysis of sequence data. Also discussed are recent methodological advances that have been made in OM and our recommendations and guidelines for future applications of OM in management research.