Cahiers du CEREMADE

Unité Mixte de Recherche du C.N.R.S. N°7534
 
Abstract : Two forms of mixtures of triangular distributions are considered as an alternative to the Bernstein polynomials for Bayesian nonparametric density estimation on $left[0,1 ight]$. Conditions for weak and strong consistency of the posterior distribution and a rate of convergence are established. This class of priors is applied to the problem of testing a parametric family against a nonparametric alternative.
 
 
Bayesian Mixtures of Triangular distributions with application to Goodness-of-Fit Testing
MCVINISH Ross, MENGERSEN K.L., ROUSSEAU Judith
2005-31
06-07-2005
 
Université de PARIS - DAUPHINE
Place du Maréchal de Lattre De Tassigny - 75775 PARIS CEDEX 16 - FRANCE
Téléphone : +33 (0)1 44-05-49-23 - fax : +33 (0)1 44-05-45-99