Least-Squares Bilinear Clustering for Three-Way Data
K-Means Over One Way of An Three-Way Array
Bilinear Decomposition of a Matrix
Double-Centre a Three-way Array
Compare LSBCLUST Simulation Results
Compare LSBCLUST Simulation Results
Compare Simulation Results
Compare LSBCLUST Simulation Results
C++ Function for Cluster Means
Centring Matrix
Extract Fitted Values for akmeans
Extract Fitted Values for LSBCLUST
Extract Fitted Values for T3Clusf
Generalized Procrustes Rotation
Create Array of Indicator Matrices
Interaction Clustering in Least Squares Bilinear Clustering
C++ Function for Weighted K-Means
C++ Function for Interaction Loss Function
Least Squares Latent Class Matrix Factorization
Least-squares Bilinear Clustering of Three-way Data
S3 export
Biplots of
Plot Heatmap of A Matrix
K-means on the Overall Mean, Row Margins or Column Margins
Plot a bicomp Object
Plot method for class 'col.kmeans'
Plot Method for Class 'int.lsbclust'
Plot method for class 'lsbclust'
Plot method for class 'ovl.kmeans'
Plot method for class 'row.kmeans'
Plot method for class 'step.lsbclust'
Plot Method for Class 'T3Clusf'
Print method for object of class 'lsbclust'
Simulate from LSBCLUST Model
Generate A Random Orthonormal Matrix
Simulate and Analyze LSBCLUST
Randomly Generate Positive Singular Values
Model Search for lsbclust
Summary Method for Class "int.lsbclust"
Summary Method for Class "lsbclust"
T3Clusf: Tucker3 Fuzzy Cluster Analysis
Functions for performing least-squares bilinear clustering of three-way data. The method uses the bilinear decomposition (or bi-additive model) to model two-way matrix slices while clustering over the third way. Up to four different types of clusters are included, one for each term of the bilinear decomposition. In this way, matrices are clustered simultaneously on (a subset of) their overall means, row margins, column margins and row-column interactions. The orthogonality of the bilinear model results in separability of the joint clustering problem into four separate ones. Three of these sub-problems are specific k-means problems, while a special algorithm is implemented for the interactions. Plotting methods are provided, including biplots for the low-rank approximations of the interactions.