Gaussian Mixture Models Based on Principal Components and Applications

Table 10

Cancer incidence data: parameter estimates and BIC of the bivariate GMM (second technique) by taking cluster means as initial values of model means.

Values	Model parameters
	First component					Second component
	Parameter estimation	0.23784	5.47040	−1.26496	70.67932	11.1214	0.76216	−1.7071	0.39475	0.25557	0.07398
Log-likelihood = −242.2075, BIC = 556.9627; Number of iterations: 30