[Master Index]
[Index for export/brede]
brede_mat_ibfa
(export/brede/brede_mat_ibfa.m)
Function Synopsis
[W1,S,W2] = brede_mat_ibfa(X, Y, varargin)
Help text
brede_mat_ibfa - Interbattery analysis
[W1,S,W2] = brede_mat_ibfa(X, Y)
Input: X 'Mat' structure
Y 'Mat' structure
Output: W1 Left 'canonical' vectors
S 'Canonical' coefficients
W2 Right 'canonical' vectors
Tucker's Interbattery factor analysis.
The results W1 and W2 are the characteristic vectors of R12'*R12
and R12*R12'. This is the same as the singular vector of the R12
correlation coefficient matrix between X and Y. S contains the
square root of the characteristic roots, i.e., the singular values.
One column in W1 and one row in W2 is one factor.
Ref: Tucker, 1958, Psychometrika 23(2):111+
Example:
% Data from Mardia 1979
load(fullfile(fileparts(which('brede')), 'data', 'FretsG1921Heredity.txt'))
X = FretsG1921Heredity(:,1:2);
Y = FretsG1921Heredity(:,3:4);
[W1,S,W2] = brede_mat_ibfa(X,Y);
diag(S.matrix)
% Text mining example
Mvoxel = brede_bib_bib2mat(B, 'type', 'Exp.Loc.coord');
Mterm0 = brede_bib_bib2mat(B, 'type', 'abstract');
M = brede_mat_elimsingle(Mterm0);
M = brede_mat_elimstop(M, 'filename', 'stop_english1.txt');
M = brede_mat_elimstop(M, 'filename', 'stop_medline.txt');
M = brede_mat_elimstop(M, 'filename', 'stop_meshcommon.txt');
M = brede_mat_elimstop(M, 'filename', 'stop_pubmed_neg1.txt');
Mterm = brede_mat_scale(M, 'type', 'sqrt');
[W1,S,W2] = brede_mat_ibfa(Mvoxel, Mterm)
brede_mat_2mat2html(W1, W2, 'filename', 'ibfa.html');
See also BREDE, BREDE_MAT, BREDE_MAT_CCA, BREDE_MAT_KMC,
BREDE_MAT_ORTHOSPACE, BREDE_MAT_SVD, BREDE_MAT_NMF.
$Id: brede_mat_ibfa.m,v 1.2 2007/11/09 00:15:19 fn Exp $
Cross-Reference Information
This function calls
This function is called by
Produced by mat2html on Fri Jun 20 17:43:05 2008
Cross-Directory links are: OFF