Co‐Clustering of Continuous Data
Gérard Govaert, Mohamed Nadif · 2013
This chapter aims to summarize the data by means of clusters of the individuals and the variables. It discusses co-clustering under metric and probabilistic approaches for continuous data. The first section describes the metric methods, which can be viewed as a minimization of a loss information function. The CROEUC algorithm is used for this purpose. In the second section, the latent block model with Gaussian distributions and associated algorithms, namely Gaussian LBCEM and LBVEM, is studied. The LBCEM and LBVEM are illustrated in the third section. The fourth section presents a Gaussian block mixture model. Two algorithms are derived which are evaluated in the fifth section.