Parameter Sensistivity and Its Cyclical Consequences in Macroeconometric Models

Ullrich Heilemann (), Heinz Josef Münsch () and Michael B. E. Ackermann ()
Additional contact information
Ullrich Heilemann: Universität Duisburg and RWI
Heinz Josef Münsch: RWI
Michael B. E. Ackermann: Universität Duisburg and RWI

No 823, Computing in Economics and Finance 1999 from Society for Computational Economics

Abstract: Since the seminal work of Adleman/Adleman, econometric models are presumed to be driven by changes of the exogenous variables, modified by the model's dynamics. Our knowledge of the impulse/propagation mechanism in macroeconometric models is, however, still rather poor. In following a more flexible understanding of econometric model parameters, laid out by Belsley/Kuh/Welsch and Kuh/Neese/Hollinger, it is suggested that parameter perturbation be used as an instrument to analyze the propagation process. Applications of the method to the Michigan Quarterly Model and to the RWI Quarterly Model revealed that only a few parameters strongly contribute to the model's reactions. The present paper extends this analysis and asks in more detail for the quantitative importance of these reactions with respect to the business cycle classification. More specifically, it examines the cyclical consequences of systematic parameter perturbations within the RWI model, a medium sized macroeconometric model for the FRG in operation for more than 25 years. As a cyclical reference, a four phase classification of the German business cycles, derived from a multivariate discriminant analysis, is used. The paper attempts to determine the degrees of parameter changes that are able to affect the cyclical picture of the economy. It first reviews the cyclical implications of macroeconometric models and then presents the notions of influential data in general and parameter perturbations in particular. It then presents the results of a number of parameter perturbations, evaluating them with respect to their cyclical consequences in the multivariate-discriminant-analysis-based classification scheme. Finally, it answers the question whether changes, if not an alternative, are at least a complement to exogenous variables in driving elements of macroeconometric models.

Date: 1999-03-01
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

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:sce:scecf9:823

Access Statistics for this paper

More papers in Computing in Economics and Finance 1999 from Society for Computational Economics CEF99, Boston College, Department of Economics, Chestnut Hill MA 02467 USA. Contact information at EDIRC.
Bibliographic data for series maintained by Christopher F. Baum ().