Jones, M. C. and Vines, S. K.
|DOI (Digital Object Identifier) Link:||http://dx.doi.org/10.1007/BF02565121|
|Google Scholar:||Look up in Google Scholar|
We consider the estimation of multinomial probabilities in the non-sparse univariate unordered case. We describe a number of explicit methods (mostly pre-existing) for the choice of the smoothing parameter in this context. In simulations, we compare these methods in terms of mean root mean squared error performance. Our recommendation is for the routine use of the simplest Bayesian estimation formula in which the probability in the k'th cell is estimated by (nk +1)/(N+K) where nk is the count in the k'th cell, N is the sample size and K is the number of cells.
|Item Type:||Journal Article|
|Copyright Holders:||1998, Springer Berlin / Heidelberg|
|Keywords:||Bayes estimation; binomial data; cross-validation; mean squared error; shrinkage; unbiasedness|
|Academic Unit/Department:||Mathematics, Computing and Technology > Mathematics and Statistics
Mathematics, Computing and Technology
|Depositing User:||Sarah Frain|
|Date Deposited:||05 May 2011 10:54|
|Last Modified:||15 Jan 2016 15:03|
|Share this page:|