Summary
For multiparameter exponential models a short and direct proof is given that the maximum likelihood estimator is a maximum probability estimator with respect to a certain sequence of convex and bounded sets inR (k) that are symmetric about the origin; asymptotically these sets are allowed to be unbounded.
Similar content being viewed by others
References
Anderson, T.W.: The integral of a symmetric unimodal function. Proc. Amer. Math. Soc.6, 1955, 170–176.
Barndorff-Nielsen, O.: Exponential Families. Exact Theory. Arhus 1970.
Berk, R.H.: Consistency and asymptotic normality of MLE's for exponential models. Ann. Math. Statist.43, 1972, 193–204.
Kaufman, S.: Asymptotic efficiency of the maximum likelihood estimator. Ann. Inst. Statist. Math.18, 1966, 155–178.
Rao, R.: Relations between weak and uniform convergence of measures with applications. Ann. Math. Statist.33, 1962, 659–680.
Weiss, L., andJ. Wolfowitz: Maximum probability estimators and related topics. Berlin-Heidelberg-New York 1974.
Witting, H., andG. Nölle: Angewandte Mathematische Statistik. Stuttgart 1970.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Kirschner, H.P. A note on the maximum probability property of MLE's in multiparameter exponential families. Metrika 24, 209–213 (1977). https://doi.org/10.1007/BF01893410
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF01893410