Discussion on Fygenson (2007, Statistica Sinica): a Ds Perspective

Some Thoughts on Future Directions in Bayesian Model Selection

As advances in computational technology have made it possible to apply Bayesian methods to situations that are increasingly complex, using a wider variety of models that are increasingly more sophisticated, problems regarding model choice are now of central importance. As a result, the development of methods for doing model selection is now at the forefront of research in Bayesian statistics. T...

Bayesian Model Selection: Some Thoughts on Future Directions

As advances in computational technology have made it possible to apply Bayesian methods to situations that are increasingly complex, using a wider variety of models that are increasingly more sophisticated, problems regarding model choice are now of central importance. As a result, the development of methods for model selection is now at the forefront of research in Bayesian statistics. This is...

Discussion of Paper by Bendel Fygenson

Nonparametric Covariance Model.

There has been considerable attention on estimation of conditional variance function in the literature. We propose here a nonparametric model for conditional covariance matrix. A kernel estimator is developed accordingly, its asymptotic bias and variance are derived, and its asymptotic normality is established. A real data example is used to illustrate the proposed estimation procedure.

Estimation in a Semi-parametric Two-stage Renewal Regression Model.

We discuss estimation in a two-stage modulated renewal process designed for analysis of paired data on a single individual. We consider a model with proportional hazard intensities. U-process methods are used to show consistency and asymptotic normality of the parameter estimates.