Non-hierarchical clustering with masloc

摘要

MASLOC is a cluster analysis technique based on the p-median model of location theory, which permits for each value of p, clustering the given objects into p groups, each provided with a representative object. Both an exact and heuristic method are described, along with their application range. The interesting values for p are then determined, along with the more interesting clusters, by robustness analysis. The paper includes a description of a computer program for MASLOC and some of the applications it was used for.