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

Abstract Details

Activity Number: 3
Type: Invited
Date/Time: Sunday, August 1, 2010 : 2:00 PM to 3:50 PM
Sponsor: General Methodology
Abstract - #306265
Title: Inference for Change-Point Parameters Under Varying Degrees of Model Misspecification
Author(s): Moulinath Banerjee*+ and Michael Kosorok and Rui Song
Companies: University of Michigan and The University of North Carolina at Chapel Hill and Colorado State University
Address: 439 West Hall, Ann Arbor, MI, 48104, USA
Keywords: change-point models ; Chernoff's distribution ; compound Poisson process ; model misspecification ; non-standard limits
Abstract:

We introduce and study a formulation of the problem of estimating change--point models under mis- specification, where the level of mis-specification is allowed to change with the sample size at various different rates. We seek to study what limit distributions ensue under what rates and develop an adaptive inference scheme that adjusts automatically to the inherent level of mis-specification in the model. Three non-standard limits arise: at rates slower than $n$, one obtains Chernoff's distribution, at faster rates the minimizer of a standard two-sided compound Poisson process, and at rate $n$, a new limit distribution resembling a compound Poisson process that depends on intrinsic parameters driving the underlying sequence of models.


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.