Events and Meetings of Italian Statistical Society, Statistics and Demography: the Legacy of Corrado Gini

Font Size: 
On a class of smoothed Good–Turing estimators
Stefano Favaro

Last modified: 2015-09-05

Abstract


Under the assumption of a two parameter Poisson-Dirichlet prior, we show that Bayesian nonparametric estimators of discovery probabilities are asymptotically equivalent, for a large sample size, to suitably smoothed Good–Turing estimators. A numerical illustration is presented to compare the performance between Bayesian nonparametric estimators with corresponding smoothed Good–Turing estimators.


Full Text: PDF