Abstract:

Multivariate density estimation plays an important role in investigating the mechanism of high-dimensional data. Here we develop a nonparametric Bayesian approach to the inference of multivariate densities. We propose a general procedure for constructing a multivariate Feller prior and establish its theoretical properties as a nonparametric prior. A blocked Gibbs sampling algorithm is proposed for simulating from the posterior of the multivariate density. Simulation studies are conducted to evaluate the performance of the procedure. 

 

Please join us to share the research experience of our fellow graduate students.

Refreshments at 3.30pm (MDS 312)

Papa John's pizza, chips, and soda