Inference When a Nuisance Parameter Is Not Identified under the Null Hypothesis

Bruce E Hansen

Econometrica, 1996, vol. 64, issue 2, 413-30

Abstract: The authors study the asymptotic distribution of econometric tests involving nuisance parameters that are not identified under the null hypotheses. In general, the asymptotic distributions depend upon a large number of unknown parameters. The authors show that a transformation based upon a conditional probability measure yields an asymptotic distribution free of nuisance parameters and they show that this transformation can be easily approximated via simulation. The theory is applied to threshold models. Monte Carlo methods are used to assess the finite sample distributions. The authors' tests show that S. M. Potter's (1995) finding of a threshold effect in U.S. GNP growth rates can be possibly explained by sampling variation. Copyright 1996 by The Econometric Society.

Date: 1996
References: Add references at CitEc
Citations: View citations in EconPapers (1455)

Downloads: (external link)
http://links.jstor.org/sici?sici=0012-9682%2819960 ... O%3B2-0&origin=repec full text (application/pdf)
Access to full text is restricted to JSTOR subscribers. See http://www.jstor.org for details.

Related works:
Working Paper: Inference when a Nuisance Parameter is Not Identified Under the Null Hypothesis (1991)
Software Item: TAR: RATS procedure to estimate a threshold autoregression, tests for threshold effect
Software Item: RATS programs to replicate Hansen's threshold estimation and testing results
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ecm:emetrp:v:64:y:1996:i:2:p:413-30

Ordering information: This journal article can be ordered from
https://www.economet ... ordering-back-issues

Access Statistics for this article

Econometrica is currently edited by Guido Imbens

More articles in Econometrica from Econometric Society Contact information at EDIRC.
Bibliographic data for series maintained by Wiley Content Delivery ().