Abstract
A fundamental statistical problem is to indicate which of two hypotheses is better supported by the data. Statistics designed for this purpose are called weight of evidence. In this paper we study the problem of robust weights of evidence, optimal in their performance while robust in the infinitesimal sense of the influence function.
Details
Title
Optimal weights of evidence with bounded influence
Author(s)
Morgenthaler, S. ; Staudte, R.
Published in
Metrika
Volume
55
Issue
1-2
Pages
91-97
Date
2002
ISSN
00261335
Laboratories
STAP
Record Appears in
Scientific production and competences > SB - School of Basic Sciences > SB Archives > STAP - Chair of Applied Statistics
Scientific production and competences > SB - School of Basic Sciences > Mathematics
Work produced at EPFL
Journal Articles
Published
Scientific production and competences > SB - School of Basic Sciences > Mathematics
Work produced at EPFL
Journal Articles
Published
Record creation date
2012-11-06