Testing in normal mixture models when the proportions are known
Bruno Goffinet, Patrice Loisel, BEATRICE LAURENT · Biometrika · 1992
The aim of this paper is to study the behaviour of the likelihood ratio test statistic in mixture models when the proportions of the distributions are known a priori. The results depend on the value of the proportion, the dimenstionality of the problem and whether or not the variance of the distributions is known.