Removing Separation Conditions in a 1 against 3-Components Gaussian Mixture Problem
In this paper we address the problem of testing homogeneity against a three components Gaussian mixture in the univariate case. As alternative we consider a contamination model. The likelihood ratio test statistic (LRTS) is derived up to an o p (1), and two separation conditions are removed. An example with real data is discussed.
Unable to display preview. Download preview PDF.
- BICKEL, P. & CHERNOFF, H. (1993). Asymptotic distribution of the likelihood ratio statistic in a prototypical non regular problem. Statistics and Probability. J.K. Ghosh et al. (eds). Wiley Eastern Limited, New-York, 83–96.Google Scholar
- GHOSH, J.K. & SEN, P.K. (1985). On the asymptotic performance of the log likelihood ratio statistic for the mixture model and related results, Proc. Berkeley Conf. in honor of Jerzy Neyman and Jack Kiefer (Vol II), L.M. Le Cam and R.A. Olshen (eds), Monterey, Wadsworth, 789–806.Google Scholar
- GOUSSANOU, Y.L.F. (2001). Asymptotics of the generalized likelihood ratio test for Gaussian mixtures. Unpublished Ph. D. Thesis, University Toulouse 3.Google Scholar
- HARTIGAN, J.A. (1985). A failure of likelihood asymptotics for normal mixtures. Proc. Berkeley Conf. in honor of Jerzy Neyman and Jack Kiefer (Vol. II), L.M. Le Cam and R.A. Olshen (eds), Monterey, Wadsworth, 807–810.Google Scholar