Some Notes on ICA
Pauliina Ilmonen · 2012
In the independent component (IC) model it is assumed that the p-variate random vector x = z + µ, where µ is a location vector, is a full rank p×p mixing matrix, and z is a p-variate vector with mutually independent components. In the independent component analysis (ICA) the aim is to find an estimate of an unmixing matrix such that x has independent components. We talk about standardization of the IC model, and on the basis of n independent copies of x, we consider one-sample testing and estimation procedures for (or ). We also discuss comparis on of different unmixing matrix estimates.