|
Activity Number:
|
483
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Thursday, August 7, 2008 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
IMS
|
| Abstract - #301684 |
|
Title:
|
Doubly Smoothed Maximum Likelihood Estimation
|
|
Author(s):
|
Byungtae Seo*+ and Bruce G. Lindsay
|
|
Companies:
|
Texas Tech University and The Pennsylvania State University
|
|
Address:
|
Department of Mathematics and Statistics, Lubbock, TX, 79409-1042,
|
|
Keywords:
|
Consistency ; Minimum distance ; kernel smoothing ; Maximum likelihood
|
|
Abstract:
|
In some models, both parametric and not, maximum likelihood estimation fails to be consistent. We show this failure of ML method with some examples and notice the paradox that, in those same models, maximum likelihood estimation would have been consistent if the data had been measured with error. With this motivation we define doubly smoothed maximum likelihood as a natural mechanism for adding measurement error. We show the proposed estimation procedure gives universal consistency in independent and identically distributed data. Some practical guidelines for the choice of kernel and tuning parameter are given. A Monte Carlo computational method is also discussed.
|
