Bootstrap validity for the score test when instruments may be weak

dc.contributorEscolas::EPGE
dc.contributorFGV
dc.creatorMoreira, Marcelo J.
dc.creatorPorter, Jack R.
dc.creatorSuarez, Gustavo A.
dc.date.accessioned2018-10-25T18:23:47Z
dc.date.available2018-10-25T18:23:47Z
dc.date.created2018-10-25T18:23:47Z
dc.date.issued2009
dc.identifier0304-4076
dc.identifierhttp://hdl.handle.net/10438/25348
dc.identifier10.1016/j.jeconom.2008.10.008
dc.identifier2-s2.0-63149101495
dc.description.abstractIt is well-known that size adjustments based on bootstrapping the t-statistic perform poorly when instruments are weakly correlated with the endogenous explanatory variable. In this paper, we provide a theoretical proof that guarantees the validity of the bootstrap for the score statistic. This theory does not follow from standard results, since the score statistic is not a smooth function of sample means and some parameters are not consistently estimable when the instruments are uncorrelated with the explanatory variable. © 2008 Elsevier B.V.
dc.languageeng
dc.relationJournal of Econometrics
dc.rightsrestrictedAccess
dc.sourceScopus
dc.subjectBootstrap
dc.subjectEdgeworth expansion
dc.subjectIdentification
dc.subjectInstrumental variable regression
dc.subjectNon-regular case
dc.subjectScore statistic
dc.subjectT-statistic
dc.subjectStatistics
dc.titleBootstrap validity for the score test when instruments may be weak
dc.typeArticle (Journal/Review)


Este ítem pertenece a la siguiente institución