Gaussian Mixture Models Based on Principal Components and Applications

Table 11

Cancer incidence data: the estimate results of fitting of the bivariate mixture model by taking cluster means as initial values of model means.

Values	Model parameters
	First component					Second component
	Parameters estimation	0.23719	5.48573	−1.26877	70.7862	11.1459	0.76281	−1.70579	0.39453	0.25765	0.07416
Log-likelihood = −242.2076, BIC = 556.9629; Number of iterations: 13