[Statlist] Research seminar in statistics October 24th 2014, GSEM, University of Geneva

Eva Cantoni Ev@@C@nton| @end|ng |rom un|ge@ch
Mon Oct 20 11:10:11 CEST 2014


Organisers : .
E. Cantoni - E. Ronchetti - S. Sperlich - M-P. Victoria-Feser

**********************************************************************************

Friday October 24th, 2014 at 11h15
Room M 5220, Uni Mail (40, bd du Pont-d'Arve)

A Prediction Divergence Criterion for Model Selection
Maria-Pia Victoria-Feser (GSEM, Université de Genève)

Abstract:
The problem of model selection is inevitable in an increasingly large 
number of applications involving partial theoretical knowledge and vast 
amounts of information, like in medicine, biology or economics. The 
associated techniques are intended to determine which variables are 
``important'' to ``explain'' a phenomenon under investigation. The terms 
``important'' and ``explain'' can have very different meanings according 
to the context and, in fact, model selection can be applied to any 
situation where one tries to balance variability with complexity. In 
this paper, we introduce a new class of error measures and of model 
selection criteria, to which most well know selection criteria belong. 
Moreover, this class enables us to derive a novel criterion, based on a 
divergence measure between the predictions produced by two nested 
models, called the Prediction Divergence Criterion (PDC). We demonstrate 
that, under some regularity conditions, for the same loss function, it 
is asymptotically loss efficient and can also be consistent. Compared to 
the $C_p$, the PDC (with a squared loss function) has a lower asymptotic 
probability of overfitting. The PDC is shown to be particularly well 
suited in ``sparse'' settings which we believe to be common in many 
research fields such as Genomics and Proteomics. Our selection procedure 
is developed for linear regression models, but has the potential to be 
extended to other models.


Visit the website: http://www.stat-center.unige.ch/ResSem.html


-- 
Prof. Eva Cantoni
Research Center for Statistics and
      Geneva School of Economics and Management
University of Geneva, Bd du Pont d'Arve 40, CH-1211 Genève 4
http://stat-center.unige.ch/members2/profs/eva-cantoni/




More information about the Statlist mailing list