A CLASSICAL INVARIANCE APPROACH TO THE NORMAL MIXTURE PROBLEM

@article{Ranalli2020ACI,
  title={A CLASSICAL INVARIANCE APPROACH TO THE NORMAL MIXTURE PROBLEM},
  author={Monia Ranalli and Bruce G. Lindsay and David R. Hunter},
  journal={Statistica Sinica},
  year={2020}
}
Although normal mixture models have received great attention and are commonly used in different fields, they stand out for failing to have a finite maximum on the likelihood. In the univariate case, there are n solutions, corresponding to n distinct data points, along a parameter boundary, each with an infinite spike of the likelihood, and none making particular sense as a chosen solution. The multivariate case yields an even more complex likelihood surface. In this paper, we show that there is… 

Figures and Tables from this paper

References

SHOWING 1-10 OF 30 REFERENCES
INFERENCE FOR NORMAL MIXTURES IN MEAN AND VARIANCE
A finite mixture of normal distributions, in both mean and variance parameters, is a typical finite mixture in the location and scale families. Because the likelihood function is unbounded for any
Inference for multivariate normal mixtures
A Constrained Formulation of Maximum-Likelihood Estimation for Normal Mixture Distributions
In this context, the normal densities are sometimes referred to as component densities. The log-likelihood function L(zy), corresponding to a random sample {xl, *, xnj, is defined by L(Ty) = Ek=1
Finite Mixture Models
TLDR
The aim of this article is to provide an up-to-date account of the theory and methodological developments underlying the applications of finite mixture models.
Constrained monotone EM algorithms for finite mixture of multivariate Gaussians
On Bayesian Analysis of Mixtures with an Unknown Number of Components (with discussion)
New methodology for fully Bayesian mixture analysis is developed, making use of reversible jump Markov chain Monte Carlo methods that are capable of jumping between the parameter subspaces
Penalized maximum likelihood estimator for normal mixtures
TLDR
The estimation of the parameters of a mixture of Gaussian densities is considered, within the framework of maximum likelihood, and a solution to likelihood function degeneracy which consists in penalizing the likelihood function is adopted.
A stochastic approximation type EM algorithm for the mixture problem
TLDR
SAEM is an adaptation of the stochastic EM algorithm that overcomes most of the well-known limitations of EM and appears to be more tractable than SEM, since it provides almost sure convergence, while SEM provides convergence in distribution.
Gaussian parsimonious clustering models
...
...