@techreport{ilprints529,
          number = {2002-11},
           month = {February},
          author = {Sepandar D. Kamvar and Dan Klein and Christopher D. Manning},
           title = {Interpreting and Extending Classical Agglomerative Clustering Algorithms using a Model-Based Approach},
            type = {Technical Report},
       publisher = {Stanford},
     institution = {Stanford InfoLab},
            year = {2002},
        keywords = {clustering, probabilistic models, model-based clustering, hierarchical clustering},
             url = {http://ilpubs.stanford.edu:8090/529/},
        abstract = {We present two results which arise from a model-based approach to hierarchical agglomerative clustering.  First, we show formally that the common heuristic agglomerative clustering algorithms -- single-link, complete-link, group-average, and Ward's method -- are each equivalent to a hierarchical model-based method.  This interpretation gives a theoretical explanation of the empirical behavior of these algorithms, as well as a principled approach to resolving practical issues, such as number of clusters or the choice of method. Second, we show how a model-based approach can be used to extend these basic agglomerative algorithms.  We introduce adjusted complete-link, Mahalanobis-link, and line-link as variants of the classical agglomerative methods, and demonstrate their utility.}
}