A Monte Carlo Study of the Sampling Distribution of the Likelihood Ratio for Mixtures of Multinormal Distributions
Abstract
Samples from spherical normal distributions were generated and fitted to hypothesized mixtures of normal distributions using the 360 NORMIX computer program for maximum likelihood estimation of the parameters of a mixture of multinormal distributions with a common covariance matrix. The results suggest that the logarithm of the likelihood ratio, when multiplied by the coefficient - 2/N(N-1-m-r/2) is distributed approximately as chi-square with degrees of freedom twice the number of variables times the difference in the numbers of hypothesized clusters. (Author)
Document Details
- Document Type
- Technical Report
- Publication Date
- Sep 01, 1971
- Accession Number
- AD0731039
Entities
People
- John H. Wolfe
Organizations
- United States Naval Research Laboratory