computes variance-covariance matrix
v=mvvacov(x)
real or complex vector or matrix
This function computes v, the matrix of variance-covariance of the "tableau" x (x is a numerical matrix nxp) who gives the values of p variables for n individuals: the (i,j) coefficient of v is v(i,j)=E(xi-xibar)(xj-xjbar), where E is the first moment of a variable, xi is the i-th variable and xibar the mean of the xi variable.
Saporta, Gilbert, Probabilites, Analyse des Donnees et Statistique, Editions Technip, Paris, 1990. Mardia, K.V., Kent, J.T. & Bibby, J.M., Multivariate Analysis, Academic Press, 1979.
Version | Description |
5.5.0 | Function tagged obsolete. Will be removed in 6.0.0. See the cov function. |
5.5.2 | mvvacov was removed after Scilab 5.5.2.
cov replaces it. |