A Priori Inequality Restrictions and Bound Analysis in VAR Models

Massimo Franchi

No 04-14, Discussion Papers from University of Copenhagen. Department of Economics

Abstract: The aim of this paper is to use inequality restrictions on the parameters of a structural model to find bounds on impulse response functions which are valid for any structural representation satisfying those restrictions. Economic theories specify signs and bounds of the coefficients which are the same among alternative paradigms: parameters are either positive or negative and propensities are between zero and one. These restrictions can thus provide a core of well established a priori impositions on which one can derive an economically meaningful interpretation of the reduced form system. Unlike just and over-identifying restrictions, inequalities select a set of structural interpretations: for this reason inference on impulse responses is derived as a bound analysis. In the last section we introduce an objective method to compare alternative under-identifying restrictions expressed as inequalities.

Keywords: VAR; identification; inequality restrictions; impulse response functions (search for similar items in EconPapers)
JEL-codes: C32 (search for similar items in EconPapers)
Pages: 17 pages
Date: 2004-07
New Economics Papers: this item is included in nep-ecm
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.econ.ku.dk/english/research/publications/wp/2004/0414.pdf/ (application/pdf)

Related works:
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:kud:kuiedp:0414

Access Statistics for this paper

More papers in Discussion Papers from University of Copenhagen. Department of Economics Oester Farimagsgade 5, Building 26, DK-1353 Copenhagen K., Denmark. Contact information at EDIRC.
Bibliographic data for series maintained by Thomas Hoffmann ().