[Statlist] Seminar ueber Statistik

Christina Kuenzli kuenz|| @end|ng |rom @t@t@m@th@ethz@ch
Mon Dec 11 11:39:28 CET 2006


              ETH and University of Zurich 

                           Proff. 
         A.D. Barbour - P. Buehlmann - F. Hampel 
              H.R. Kuensch - S. van de Geer

***********************************************************    
       We are glad to announce the following talk
***********************************************************

       Friday, December 15, 2006, 15.15, LEO C 6

       On the size of testing procedures  

       Patrik Guggenberger
       UCLA Economics, Los Angeles
 
The talk contains material of several papers, in particular: 
I The limit of finite sample size and a problem with subsampling.
II Hybrid and size-corrected subsampling methods.

The current versions of these two papers are available for download at
my webpage at http://www.econ.ucla.edu/people/faculty/Guggenberger.html
I suggest waiting with the download as long as possible. We should have
the final versions of the papers up within the next week.

A shortened combined abstract for Papers I and II is:

We consider inference based on a test statistic that has a limit
distribution that is discontinuous in a nuisance parameter or the
parameter of interest. The paper shows that subsample, $b<n$ bootstrap,
and standard fixed critical value tests based on such a test statistic
often have asymptotic size---defined as the limit of the finite-sample
size---that is greater than the nominal level of the tests. We determine
precisely the asymptotic size of such tests under a general set of
high-level conditions that are relatively easy to verify. The high-level
conditions are verified in several examples. Analogous results are
established for confidence intervals (CI).
We then consider the problem of constructing tests and CIs that have
correct asymptotic size in a broad class of non-regular models. First,
procedures are introduced that are a hybrid of subsample and fixed
critical value methods. The resulting hybrid procedures are easy to
compute and have correct size asymptotically in many, but not all, cases
of interest. Second, the paper introduces size-correction and "plug-in"
size-correction methods for fixed critical value, subsample, and hybrid
tests. The paper also introduces finite-sample adjustments for subsample
and hybrid methods and employs these adjustments in size-correction.


***********************************************************
________________________________________________________
Christina Kuenzli            <kuenzli using stat.math.ethz.ch>
Seminar fuer Statistik      
Leonhardstr. 27,  LEO D11      phone: +41 (0)44 632 3438         
ETH-Zentrum,                   fax  : +41 (0)44 632 1228 
CH-8092 Zurich, Switzerland        http://stat.ethz.ch/~




More information about the Statlist mailing list