Abstract Details
|
Activity Number:
|
665
|
|
Type:
|
Invited
|
|
Date/Time:
|
Thursday, August 8, 2013 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Host Chapter-Montreal
|
| Abstract - #306994 |
|
Title:
|
Model Selection Criteria of Singular Statistical Models
|
|
Author(s):
|
Sumio Watanabe*+
|
|
Companies:
|
Tokyo Institute of Technology
|
|
Keywords:
|
Singular learning theory ;
Information criterion ;
Algebraic geometry ;
resolution of singularities ;
WAIC ;
WBIC
|
|
Abstract:
|
A lot of statistical models which contain hidden variables, hierarchical structures, and grammatical rules do not satisfy the regularity condition, hence conventional asymptotic theory does not hold. In this talk, we show that algebraic geometrical representation of the paramater space enables us to make singular asymptotic theory, resulting that universal information criteria can be derived. Information criteria, WAIC and WBIC respectively correspond to the predictive log likelihood and the log Bayes marginal likelihood, even if a true distriution is singular for and unrealizable by a statistical model.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2013 program
|
2013 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.
The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
Copyright © American Statistical Association.