A new solution to the old problem of partitioning a matrix of social proximities into groups is proposed. It draws on a heuristic developed in computer science, the simple genetic algorithm. The algorithm is described and its utility is demonstrated with applications to three standard data sets.
Notes
This paper has benefitted greatly from suggestions made by several colleagues. In particular, the sage counsel provided by Morry Sunshine has helped to eliminate many of its earlier inadequacies. The program described here, GROUPS, is available from the author on request.