File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Likelihood estimation and inference in threshold regression

TitleLikelihood estimation and inference in threshold regression
Authors
KeywordsBayes
Boundary
Compound Poisson process
Credible set
Efficiency bounds
Local asymptotic minimax
Middle-point MLE
Nonregular models
Structural change
Threshold regression
WienerHopf equation
Issue Date2012
Citation
Journal of Econometrics, 2012, v. 167, n. 1, p. 274-294 How to Cite?
AbstractThis paper studies likelihood-based estimation and inference in parametric discontinuous threshold regression models with i.i.d. data. The setup allows heteroskedasticity and threshold effects in both mean and variance. By interpreting the threshold point as a "middle" boundary of the threshold variable, we find that the Bayes estimator is asymptotically efficient among all estimators in the locally asymptotically minimax sense. In particular, the Bayes estimator of the threshold point is asymptotically strictly more efficient than the left-endpoint maximum likelihood estimator and the newly proposed middle-point maximum likelihood estimator. Algorithms are developed to calculate asymptotic distributions and risk for the estimators of the threshold point. The posterior interval is proved to be an asymptotically valid confidence interval and is attractive in both length and coverage in finite samples. © 2011 Elsevier B.V. All rights reserved.
Persistent Identifierhttp://hdl.handle.net/10722/202149
ISSN
2015 Impact Factor: 1.611
2015 SCImago Journal Rankings: 3.781
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorYu, Ping-
dc.date.accessioned2014-08-22T02:57:43Z-
dc.date.available2014-08-22T02:57:43Z-
dc.date.issued2012-
dc.identifier.citationJournal of Econometrics, 2012, v. 167, n. 1, p. 274-294-
dc.identifier.issn0304-4076-
dc.identifier.urihttp://hdl.handle.net/10722/202149-
dc.description.abstractThis paper studies likelihood-based estimation and inference in parametric discontinuous threshold regression models with i.i.d. data. The setup allows heteroskedasticity and threshold effects in both mean and variance. By interpreting the threshold point as a "middle" boundary of the threshold variable, we find that the Bayes estimator is asymptotically efficient among all estimators in the locally asymptotically minimax sense. In particular, the Bayes estimator of the threshold point is asymptotically strictly more efficient than the left-endpoint maximum likelihood estimator and the newly proposed middle-point maximum likelihood estimator. Algorithms are developed to calculate asymptotic distributions and risk for the estimators of the threshold point. The posterior interval is proved to be an asymptotically valid confidence interval and is attractive in both length and coverage in finite samples. © 2011 Elsevier B.V. All rights reserved.-
dc.languageeng-
dc.relation.ispartofJournal of Econometrics-
dc.subjectBayes-
dc.subjectBoundary-
dc.subjectCompound Poisson process-
dc.subjectCredible set-
dc.subjectEfficiency bounds-
dc.subjectLocal asymptotic minimax-
dc.subjectMiddle-point MLE-
dc.subjectNonregular models-
dc.subjectStructural change-
dc.subjectThreshold regression-
dc.subjectWienerHopf equation-
dc.titleLikelihood estimation and inference in threshold regression-
dc.typeArticle-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1016/j.jeconom.2011.12.002-
dc.identifier.scopuseid_2-s2.0-84856362463-
dc.identifier.volume167-
dc.identifier.issue1-
dc.identifier.spage274-
dc.identifier.epage294-
dc.identifier.isiWOS:000300863300017-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats