Cluster analysis is “a generic name for a variety of mathematical methods numbering in the hundreds that can be used to find out which objects in a set are similar” (Romesburg, 2004; p. 2). With cluster analysis, typically observations (cases) are grouped together based on how similar they are to each other with regards to certain variables. Cluster analysis is often used as an exploratory technique, although it can also be used in a confirmatory role (Fisher & Ransom, 1995). Cluster analysis has been employed in a number of studies in the entrepreneurship literature (Birley and Westhead, 1994; Gibcus et al., 2009; McMahon 2001) However, as noted by Ketchen and Shook (1996) cluster analysis is subject to a number of limitations, such as its reliance on researcher judgment, the absence of statistical tests to reject or fail to reject hypotheses, and a lack of a theoretical basis for developing clusters. When using cluster analysis on a set of data, a set of clusters will be generated by the algorithm, regardless of whether groups that are substantially distinct from each other actually exist (Barney & Hoskisson, 1990; Hatten & Schendel, 1977).
Crum, Michael D. and Nelson, Thomas E.
"THE USE OF CLUSTER ANALYSIS IN ENTREPRENEURSHIP RESEARCH: REVIEW OF PAST RESEARCH AND FUTURE DIRECTIONS (SUMMARY),"
Frontiers of Entrepreneurship Research: Vol. 35
, Article 17.
Available at: http://digitalknowledge.babson.edu/fer/vol35/iss16/17