|
Activity Number:
|
125
- Bayesian Methods for Discrete Data Problems
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, July 31, 2017 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Bayesian Statistical Science
|
|
Abstract #322550
|
|
|
Title:
|
Bayesian Regression Modeling with the Tilted Beta Distribution
|
|
Author(s):
|
Eugene Hahn*
|
|
Companies:
|
Salisbury University
|
|
Keywords:
|
Percentage data ;
Finite mixture ;
Predictive modeling ;
Markov chain Monte Carlo
|
|
Abstract:
|
Regression modeling of proportions is important for many disciplines. However, the existence of boundary values at zero or one causes major difficulties for most long-standing approaches. Recent developments in handling these values involve non-smooth boundary-inflated distributions where spikes are placed at zero and one. Here we use the recently described tilted beta distribution for continuous regression modeling of proportions including boundary values.
|
Authors who are presenting talks have a * after their name.
