|
Activity Number:
|
432
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Wednesday, August 6, 2008 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Bayesian Statistical Science
|
| Abstract - #301401 |
|
Title:
|
Density Estimation for Bivariate Angular Data Using a von Mises Distribution and Bayesian Nonparametrics
|
|
Author(s):
|
Kristin P. Lennox*+ and David B. Dahl and Marina Vannucci and Jerry Tsai
|
|
Companies:
|
Texas A&M University and Texas A&M University and Rice University and Texas A&M University
|
|
Address:
|
Department of Statistics, College Station, TX, 77843-3143,
|
|
Keywords:
|
Circular data ; Dihedral angles ; Dirichlet process mixture model ; Protein conformational angles ; Torsion angles
|
|
Abstract:
|
Interest in modeling protein backbone conformational angles has prompted the development of bivariate angular distributions, as well as frequentist methods for fitting mixtures of these distributions to data. We present a Bayesian approach to density estimation for bivariate angular data that uses a Dirichlet process mixture (DPM) model and the bivariate von Mises distribution. We derive the necessary full conditional distributions to fit such a model, as well as the details for sampling from the posterior predictive distribution. This method is used to estimate the main-chain torsion angle distributions from the immunoglobulin protein structure family.
|
