Glenn W. Milligan

Learn More
Five external criteria were used to evaluate the extent of recovery of the true structure in a hierarchical clustering solution. This was accomplished by comparing the partitions produced by the clustering algorithm with the partition that indicates the true cluster structure known to exist in the data. The five criteria examined were the Rand, the Morey(More)
Mass customization is a paradox-breaking manufacturing reality that combines the unique products of craft manufacturing with the cost-efficient manufacturing methods of mass production. Although this phenomenon is known to exist in practice, academic research has not adequately investigated this new form of competition. In this research, we develop a(More)
An evaluation of four clustering methods and four external criterion measures was conducted with respect to the effect of the number of clusters, dimensionality, and relative cluster sizes on the recovery of true cluster structure. The four methods were the single link, complete link, group average (UPGMA), and Ward's minimum variance algorithms. The(More)
A review of Monte Carlo validation studies of clustering algorithms is presented. Several validation studies have tended to support the view that Ward's minimum variance hierarchical method gives the best recovery of cluster structure. However, a more complete review of the validation literature on clustering indicates that other algorithms may provide(More)
Finite and asymptotic formulas are derived for the Rand, adjusted Rand, Fowlkes and Mallows, and Jaccard external criterion measures. The formulas were developed for ten clustering situations which have been used previously in the clustering literature. The results indicated that the Jaccard and Fowlkes and Mallows measures were fairly similar. The Rand and(More)
The beta-flexible clustering method has exhibited good recovery performance in the few comparative simulation studies that have included the procedure. Further, the beta-flexible technique has not been examined in a systematic manner over the range of parameter values that can be specified for the method. The present report was designed to provide a more(More)
We introduce a UPGMA based counterpart to the Lance and Williams (1966) p-flexible clustering strategy. This new method is compared with the original p-flexible technique based on WPGMA for a range of fl values from -0.8 to +0.1. Recovery of the known cluster structure from simulated data was evaluated using the Hubert and Arabie (1985) version of the Rand(More)
The Supply Chain Operations Reference (SCOR) model has been widely adopted in many companies. Anecdotal evidence and trade journals have reported significant improvements after firms have adopted the SCOR model. Although practitioners have been enthusiastic about implementing and using the SCOR model in their operations, the SCOR model has not been(More)
Three-dimensional response surface plots arc presented for several hierarchical clustering methods and simulated core group data structures. The response surface represents the relative influence of the corresponding coordinate location in the bivariate data space on the clustering of the core groups. lnfluence is defined as a change in the clustering of(More)