Abstract
A frequently occurring problem is to find the maximum likelihood estimation (MLE) of p subject to p∈C (C⊂ P the probability vectors in R k). The problem has been discussed by many authors and they mainly focused when p is restricted by linear constraints or log-linear constraints. In this paper, we construct the relationship between the the maximum likelihood estimation of p restricted by p∈C and EM algorithm and demonstrate that the maximum likelihood estimator can be computed through the EM algorithm (Dempster et al. in J R Stat Soc Ser B 39:1–38, 1997). Several examples are analyzed by the proposed method.
Similar content being viewed by others
References
Barmi HEL, Dykstra RL (1994) Restricted multinomial maximum likelihood estimation based upon Frenchel duality. Stat Probab Lett 21:121–130
Barmi HEL, Dykstra RL (1998) Maximum likelihood estimates via duality for log-convex models when cell probabilities are subject to convex constraints. Ann Stat 26:1878–1983
Chacko VJ (1966) Modified chi-square test for ordered alternatives. Sankhya Ser B 28:185–190
Darroch JN, Ratcliff D (1972) Generalized iterative scaling for log-linear models. Ann Math Stat 43:1470–1480
Dempster AP, Laird NM, Rubin DB (1977) Maximum likelihood from incomplete data via the EM algorithm (with discussion). J R Stat Soc Ser B 39:1–38
Dykstra RL, Robertson T (1982) Order restricted statistical tests on multinomial and Poisson parameters: the starshaped restriction. Ann Stat 10:1246–1252
Gokhale DV (1973) Iterative maximum likelihood for discrete distributions. Sankhya Ser B 35:293–298
Haber M (1985) Maximum likelihood methods for linear and loglinear models in categorical data. Comput Stat Data Anal 3:1–10
Kullback S (1967) An extension of information-theoretic derivation of certain limit relations for a Markov chain. SIAM J Control 5:51–53
Lee CC, Yan X, Shi NZ (1999) Nonparametric estimation of bounded survival functions with censored observations. Lifetime Data Anal 5:81–90
Lemke JH, Dykstra RL (1984) An algorithm for multinomial maximum likelihood estimation with multiple cone restrictions. In: Techical report 84–1, Department of Preventive Medicine, University of Iowa
Liu C (2000) Estimation of descrete distributions with a class of simplex constraints. J Am Stat Assoc 95:109–120
Shi NZ, Jiang H (1998) Maximum likelihood estimation of isotonic normal mean with unknown variances. J Multivariate Anal 64:183–196
Stuart A (1953) The estimation and comparison of strength of association in contingency table. Biometrika 40:105–110
Stuart A (1955) A test for homogeneity of marginal distribution in a two-way classification. Biometrika 42:412–416
Wedderburn RWM (1974) General linear models specified in terms of constraints. J R Stat Soc Ser B 36:449–454
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Li, Y., Gao, W. & Shi, NZ. A note on multinomial maximum likelihood estimation under ordered restrictions and the EM algorithm. Metrika 66, 105–114 (2007). https://doi.org/10.1007/s00184-006-0098-z
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00184-006-0098-z