Auteurs Centres de recherche Disciplines et Collections Projets
Français English
 
 

Dilatation Bootstrap : a methodology for constructing confidence regions with partially identified models

 

Notice

Type:   Article
 
Titre:   Dilatation Bootstrap : a methodology for constructing confidence regions with partially identified models
 
Auteur(s):   Galichon, Alfred (1977-...) - Département d'économie (Auteur)
Henry, Marc - Départment de sciences économiques (Auteur)
 
In:   Journal of Econometrics
 
Date de publication:   2013
 
Éditeur:   PAYS-BAS  :  Elsevier
 
Volume:   177
 
Numéro:   1
 
Pages:   109-115  p.
 
Notes:   In press (accepted manuscript).
 
ISSN:   03044076
 
Mots-clés:   [fr] Partial identification; Dilation bootstrap; Quantile process; Optimal matching
 
JEL:   C15,  C31
 
Résumé:   [en] We propose a methodology for constructing confidence regions with partially identified models of general form. The region is obtained by inverting a test of internal consistency of the econometric structure. We develop a dilation bootstrap methodology to deal with sampling uncertainty without reference to the hypothesized economic structure. It requires bootstrapping the quantile process for univariate data and a novel generalization of the latter to higher dimensions. Once the dilation is chosen to control the confidence level, the unknown true distribution of the observed data can be replaced by the known empirical distribution and confidence regions can then be obtained as in Galichon and Henry (2011) and Beresteanu, Molchanov and Molinari (2011).
 
 

Résolveur de liens