PROBABILITY DENSITY-ESTIMATION USING A GAUSSIAN CLUSTERING-ALGORITHM

A version of the Traven's [1] Gaussian clustering algorithm for normal mixture densities is studied. Unlike in the case of the Tuaven's algo rithm, no constraints on covariance structure of mixture components ar e imposed. Simulations suggest that the modified algorithm is a very p romising method of estimating arbitrary continuous d-dimensional densi ties. In particular, the simulations have shown that the algorithm is robust against assuming the initial number of mixture components to be too large.