Bayesian shrinkage estimation of negative multinomial parameter vectors

Abstract The negative multinomial distribution is a multivariate generalization of the negative binomial distribution. In this paper, we consider the problem of estimating an unknown matrix of probabilities on the basis of observations of negative multinomial variables under the standardized squared error loss. First, a general sufficient condition for a shrinkage estimator to dominate the UMVU estimator is derived and an empirical Bayes estimator satisfying the condition is constructed. Next, a hierarchical shrinkage prior is introduced, an associated Bayes estimator is shown to dominate the UMVU estimator under some conditions, and some remarks about posterior computation are presented. Finally, shrinkage estimators and the UMVU estimator are compared by simulation.

[1]  M. E. Muldoon.  Some monotonicity properties and characterizations of the gamma function , 1977 .

[2]  Kam-Wah Tsui.  Estimation of poisson means under weighted squared error loss , 1979 .

[3]  Fumiyasu Komaki.  A class of proper priors for Bayesian simultaneous prediction of independent Poisson observables , 2006 .

[4]  Masaaki Sibuya,et al.  Negative multinomial distribution , 1964 .

[5]  Kam-Wah Tsui.  Multiparameter estimation for some multivariate discrete distributions with possibly dependent components , 1986 .

[6]  Fumiyasu Komaki,et al.  Simultaneous prediction of independent Poisson observables , 2004, math/0410094.

[7]  Kam-Wah Tsui.  Robustness of Clevenson-Zidek-Type Estimators , 1984 .

[8]  M. Ghosh,et al.  Bayes minimax estimation of multiple Poisson parameters , 1981 .

[9]  E. L. Lehmann,et al.  Theory of point estimation , 1950 .

[10]  H. Hudson.  A Natural Identity for Exponential Families with Applications in Multiparameter Estimation , 1978 .

[11]  Kam-Wah Tsui.  Further developments on the robustness of Clevenson-Zidek-type means estimators , 1986 .

[12]  T. Kubokawa,et al.  Simultaneous estimation of parameters of Poisson distributions with unbalanced sample sizes , 2019, Japanese Journal of Statistics and Data Science.

[13]  Malay Ghosh,et al.  Simultaneous Estimation of Poisson Means Under Entropy Loss , 1988 .

[14]  Kam-Wah Tsui,et al.  Simultaneous Estimation of Several Poisson Parameters Under $K$-Normalized Squared Error Loss , 1982 .

[15]  T. Kubokawa,et al.  Proper Bayes minimax estimation of parameters of Poisson distributions in the presence of unbalanced sample sizes , 2020 .

[16]  Jiunn Tzon Hwang,et al.  Improving Upon Standard Estimators in Discrete Exponential Families with Applications to Poisson and Negative Binomial Cases , 1982 .

[17]  Dipak K. Dey,et al.  Compound Poisson distributions : properties and estimation , 1992 .

[18]  Kam-Wah Tsui,et al.  Multiparameter estimation of discrete exponential distributions , 1979 .

[19]  Fumiyasu Komaki,et al.  Simultaneous prediction for independent Poisson processes with different durations , 2014, J. Multivar. Anal..

[20]  M. Ghosh,et al.  Construction of Improved Estimators in Multiparameter Estimation for Discrete Exponential Families , 1983 .

[21]  Nils Lid Hjort,et al.  Multivariate estimation of Poisson parameters , 2019, J. Multivar. Anal..

[22]  J. Zidek,et al.  Simultaneous Estimation of the Means of Independent Poisson Laws , 1975 .