Multiblock analysis combines two data matrices derived from the same samples and uses them to build models based on consensus. They are particularly useful for combining information from multiple experimental methods, such as NMR and MS but can also be used to combine information from different lab techniques, or to compare extraction methods, or compare data obtained from different collaborators.
For more information see:
J. Westerhuis, T. Kourti, J. F. MacGregor. ‘Analysis of Multiblock and Hierarchical PCA and PLS models’, Journal of Chemometrics, 1998(21): 301-321.
Note: Here we assume you already have 2 independent experimental matrices, denoted X1 and X2, that are already loaded and pre-processed as desired. X1 and X2 must have the same number of rows (equivalent first dimensions), but the number of columns is unconstrained.
%Concatenating X1 and X2 into a single multiblock array X=multiblock(X1,X2); %Some possible modeling options mb_pca=mbpca(X); mb_pls=mbpls(X); mb_opls=mbopls(X);
After you generate the model, it is compatible with all of the other techniques available for visualzation and validation of mvapack-generated models.