Internal function required for fitting a mixture of PPCA models.
mstep1(Y, Tau, Pi, mu, g)A N x p data matrix.
An N x G matrix of posterior group membership probabilities.
A g vector of group probabilities.
A p x g matrix containing the mean for each group.
The number of groups currently being fitted.
A list containing
A g vector of group probabilities
A p x g matrix each column of which contains a group mean.
First M-step of the AECM algorithm when fitting a mixture of PPCA models. An internal function.
Nyamundanda, G., Gormley, I.C. and Brennan, L. (2010) Probabilistic principal components analysis for metabolomic data. Technical report. University College Dublin, Ireland.