English

Testing the Order of Multivariate Normal Mixture Models

Statistics Theory 2019-02-11 v1 Econometrics Statistics Theory

Abstract

Finite mixtures of multivariate normal distributions have been widely used in empirical applications in diverse fields such as statistical genetics and statistical finance. Testing the number of components in multivariate normal mixture models is a long-standing challenge even in the most important case of testing homogeneity. This paper develops likelihood-based tests of the null hypothesis of M0M_0 components against the alternative hypothesis of M0+1M_0 + 1 components for a general M01M_0 \geq 1. For heteroscedastic normal mixtures, we propose an EM test and derive the asymptotic distribution of the EM test statistic. For homoscedastic normal mixtures, we derive the asymptotic distribution of the likelihood ratio test statistic. We also derive the asymptotic distribution of the likelihood ratio test statistic and EM test statistic under local alternatives and show the validity of parametric bootstrap. The simulations show that the proposed test has good finite sample size and power properties.

Keywords

Cite

@article{arxiv.1902.02920,
  title  = {Testing the Order of Multivariate Normal Mixture Models},
  author = {Hiroyuki Kasahara and Katsumi Shimotsu},
  journal= {arXiv preprint arXiv:1902.02920},
  year   = {2019}
}

Comments

54 pages, 2 figures

R2 v1 2026-06-23T07:35:16.039Z