Posterior Consistency in Conditional Density Estimation by Covariate Dependent Mixtures
This paper considers Bayesian nonparametric estimation of conditional densities by countable mixtures of location-scale densities with covariate dependent mixing probabilities. The mixing probabilities are modeled in two ways. First, we consider finite covariate dependent mixture models, in which the mixing probabilities are proportional to a product of a constant and a kernel and a prior on the number of mixture components is specified. Second, we consider kernel stick-breaking processes for modeling the mixing probabilities. We show that the posterior in these two models is weakly and strongly consistent for a large class of data generating processes.
|Date of creation:||Dec 2011|
|Contact details of provider:|| Postal: Josefstädterstr. 39, A-1080 Vienna, Austria|
Phone: ++43 - (0)1 - 599 91 - 0
Fax: ++43 - (0)1 - 599 91 - 555
Web page: http://www.ihs.ac.at
More information through EDIRC
|Order Information:|| Postal: Institute for Advanced Studies - Library, Josefstädterstr. 39, A-1080 Vienna, Austria|
When requesting a correction, please mention this item's handle: RePEc:ihs:ihsesp:282. See general information about how to correct material in RePEc.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (Doris Szoncsitz)
If references are entirely missing, you can add them using this form.