On maximum likelihood estimation in the moverstayer model
- 1 January 1996
- journal article
- research article
- Published by Taylor & Francis in Communications in Statistics - Theory and Methods
- Vol. 25 (8) , 1717-1728
- https://doi.org/10.1080/1532415X.1996.11877449
Abstract
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.Keywords
This publication has 5 references indexed in Scilit:
- A Markov Chain Model for Unskilled Workers and the Highly MobileJournal of the American Statistical Association, 1990
- Maximum Likelihood Estimation in the Mover-Stayer ModelJournal of the American Statistical Association, 1984
- On the Convergence Properties of the EM AlgorithmThe Annals of Statistics, 1983
- Parameter Estimation for Mover-Stayer ModelsSociological Methods & Research, 1983
- Statistical Methods for the Mover-Stayer ModelJournal of the American Statistical Association, 1961