|
Activity Number:
|
427
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 5, 2009 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Bayesian Statistical Science
|
| Abstract - #305207 |
|
Title:
|
Bayesian Regression Inference in Knot Theory
|
|
Author(s):
|
John Kern*+ and Eric Rawdon
|
|
Companies:
|
Duquesne University and St. Thomas University
|
|
Address:
|
600 Forbes Avenue, Pittsburgh, PA, 15282,
|
|
Keywords:
|
Gibbs sampling ; MCMC ; Knot theory
|
|
Abstract:
|
This research explores a Bayesian regression model used to estimate the mean box length of a random knot as a function of the number of edges of that knot. Of particular interest in this application is the crossing location of two such population regression lines. The Bayesian model is shown to allow straightforward inference on this crossing location, and is implemented under conditions well-suited for empirical Bayes.
|
