On maximum likelihood estimation in the moverstayer model
Anders Rygh Swensen · Communication in Statistics- Theory and Methods · 1996
We derive the profile likelihood function of the mixing parameters in the discrete time mover-stayer model This result is used to find a simple necessary and sufficient condition for the maximum Ekelihood estimator to take values in the interior of the parameter space, We point out the relevance of this result for the convergence properties of the EM algorithm, Furthermore, the likelihood-ratio test for the hypothesis that there are equality constraints among the mixing parameters is developed. Finally an illustration of the use of the results is given.