Premium
Emergent clustering methods for empirical OM research
Author(s) -
Brusco Michael J.,
Steinley Douglas,
Cradit J. Dennis,
Singh Renu
Publication year - 2012
Publication title -
journal of operations management
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 3.649
H-Index - 191
eISSN - 1873-1317
pISSN - 0272-6963
DOI - 10.1016/j.jom.2012.06.001
Subject(s) - cluster analysis , computer science , scope (computer science) , data science , empirical research , software , data mining , management science , machine learning , engineering , mathematics , statistics , programming language
To date, the vast majority of cluster analysis applications in OM research have relied on traditional hierarchical (e.g., Ward's algorithm) and nonhierarchical (e.g., K ‐means algorithms) methods. Although these venerable methods should continue to be employed effectively in the OM literature, we also believe there is a significant opportunity to expand the scope of clustering methods to emergent techniques. We provide an overview of some alternative clustering procedures (including advantages and disadvantages), identify software programs for implementing them, and discuss the circumstances where they might be employed gainfully in OM research. The implementation of emergent clustering methods in the OM literature should enable researchers to offer implications for practice that might not have been uncovered with traditional methods.