Comments on ``Application of the Conditional Population-Mixture Model to Image Segmentation''
- 1 September 1984
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. PAMI-6 (5) , 656-658
- https://doi.org/10.1109/TPAMI.1984.4767581
Abstract
In the above correspondence1 a maximum likelihood method is proposed for ``estimating'' class memberships and underlying statistical parameters, within the context of distribution mixtures. In the present comment it is pointed out that biases are incurred in parameter estimation, that the class memberships and parameters are conceptually different, and therefore that the so-called standard mixture likelihood is to be preferred. Also in the correspondence,1 Akaike's information criterion (AIC) is used to choose the number of classes in the mixture. Here a brief theoretical caveat is issued.Keywords
This publication has 13 references indexed in Scilit:
- On Jointly Estimating Parameters and Missing Data by Maximizing the Complete-Data LikelihoodThe American Statistician, 1983
- Likelihood of a model and information criteriaJournal of Econometrics, 1981
- Clustering Criteria and Multivariate Normal MixturesPublished by JSTOR ,1981
- Finite Mixture DistributionsPublished by Springer Nature ,1981
- Asymptotic behaviour of classification maximum likelihood estimatesBiometrika, 1978
- A quasi-Bayes unsupervised learning procedure for priors (Corresp.)IEEE Transactions on Information Theory, 1977
- 389: Separating Mixtures of Normal DistributionsPublished by JSTOR ,1975
- A new look at the statistical model identificationIEEE Transactions on Automatic Control, 1974
- On decision-directed estimation and stochastic approximation (Corresp.)IEEE Transactions on Information Theory, 1972
- Clustering Methods Based on Likelihood Ratio CriteriaPublished by JSTOR ,1971