Abstract
Characterizations of gamma-minimax predictors for the linear combinations of the unknown parameter and the random variable having the multinomial distribution under arbitrary squared error loss are established in two situations – when the sample size is fixed and when the sample size is a realization of a random variable. It is always assumed that the available vague prior information about the unknown parameter can be described by a class of priors whose vector of first moments belongs to a suitable convex and compact set. Several known gamma-minimax and minimax results can be obtained from the characterizations derived in the present paper.
Similar content being viewed by others
References
Amrhein P (1995) Minimax estimation of proportions under random sample size. J Am Stat Assoc 90:1107–1111
Brockmann M, Eichenauer-Herrmann J (1992) Gamma-minimax estimation of multinomial probabilities. App Math 21:427–435
Brown LD (1990) An ancillarity paradox which appears in multiple linear regression. Ann Stat 18:471–493
Chen L, Eichenauer-Herrmann J, Lehn J (1990) Gamma-minimax estimators for the parameters of a multinomial distribution. Appl Math 20:561–564
He K (1990) An ancillarity paradox in the estimation of multinomial probabilities. J Am Stat Assoc 85:824–828
Jokiel-Rokita A (1998) Minimax prediction for the multinomial and multivariate hypergeometric distributions. Appl Math 25:271–283
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Jokiel-Rokita, A. Gamma-Minimax Prediction for the Multinomial Distribution. Metrika 64, 259–269 (2006). https://doi.org/10.1007/s00184-006-0047-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00184-006-0047-x