This is the program for the 2010 Joint Statistical Meetings in Vancouver, British Columbia.

Abstract Details

Activity Number: 428
Type: Contributed
Date/Time: Tuesday, August 3, 2010 : 2:00 PM to 3:50 PM
Sponsor: Section on Statistics and the Environment
Abstract - #307627
Title: Binary Markov Random Fields with Absorbing States
Author(s): Nick Larson*+ and Amy Hoeksema and Karl Pazdernik and Mark Kaiser
Companies: Iowa State University and Iowa State University and Iowa State University and Iowa State University
Address: , , ,
Keywords: spatial ; Markov Random Fields ; Absorbing States
Abstract:

When modeling spatial problems in statistics using Markov Random Fields, there exists a necessary positivity condition. However, given a situation in which this assumption has been violated through the presence of a natural absorbing state presents a new problem. We introduce a new approach using a Binary Markov Random Field along with a Markov property in time. At each point in time, any random variable that has reached the absorbing state must be removed from the model since it can no longer be considered a random variable. To adjust for the decreasing number of random variables in the model, each is replaced by a constant dependence term. We will justify the use of this adjusted model and present a real life situation for which this model was motivated. We will demonstrate both maximum likelihood and Bayesian approaches to fitting the model.


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 2010 program




2010 JSM Online Program Home

For information, contact jsm@amstat.org or phone (888) 231-3473.

If you have questions about the Continuing Education program, please contact the Education Department.