Statis-linear discriminant analysis method
result = statislda(Xtab,Y,(RV));
the different datasets, as a list
Xtab(i) is a matrix of dimensions (n x pi) or a Div structure
the sum of the pi yields p
the class of each observation
Y is a conjunctive vector or a disjunctive matrix or a Div structure of conjunctive or disjunctive data
t: normalization of the matrix C
f: no normalization (by default)
axes of Statis-LDA
result.p.d is a matrix of dimensions (p x n_axes)
the scores of the observations on the axes of Statis-LDA
result.t.d is a matrix of dimensions (n x n_axes)
the scores of the barycenters of the q tables
result.tg.d is a matrix of dimensions (q x n_axes)
the norms of the q operators associated to the LDA of (Xi, Y)
result.normw.i is a vector of dimensions (q x 1)
matrix of the inner products between the q operators
result.cmatrix.d is a matrix of dimensions (q x q)
eigenvectors of cmatrix
result.cmatrix_eigenvec.d is a matrix of dimensions (q x q)
coefficients of the compromise after diagonalization of cmatrix
result.cc.d is a vector of dimensions (q x 1)
the variance-covariance matrix of the compromise
result.vtot.d is a matrix of dimensions (p x p)
eigenvectors of vtot
result.vtot_eigenvec.d is a matrix of dimensions (p x n_axes)
eigenvalues of vtot
result.vtot_eigenval.d is a vector of dimensions (n_axes x 1)
mean of the data merged by columns
result.xconc_mean.d is a vector of dimensions (p x 1)