|
Activity Number:
|
132
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, August 3, 2009 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Bayesian Statistical Science
|
| Abstract - #303603 |
|
Title:
|
In Search of Sasquatch
|
|
Author(s):
|
Jennifer B. Emerson*+ and Robert F. Martin and Bo He and Clyde Martin
|
|
Companies:
|
Texas Tech University and Federal Reserve Board and The University of Texas and Texas Tech University
|
|
Address:
|
, Lubbock, TX, 79409,
|
|
Keywords:
|
urn ; bayesian ; learning
|
|
Abstract:
|
A problem in field biology is the search for a species that may or may not be present. It might be as simple as determining if a species of dragonfly has enlarged its range or as esoteric as trying to find the elusive Sasquatch. The primary question is, Does it not exist or have I just failed to find it? We model this using a simple urn model. We assume an urn with an unknown, but small, number of black balls and a large number of white balls. We assume two different priors. The first prior is an exponential and the second is a characteristic function. The posterior is determined by updating using Bayesian updating. The case of interest is when no black balls are drawn. In the first case the expected value goes to zero and the agent can become confident that the object does not exist. In the second case no matter how many white balls are drawn there is still hope that the object exists.
|
- The address information is for the authors that have a + after their name.
- Authors who are presenting talks have a * after their name.
Back to the full JSM 2009 program |
