Testing increasing dispersion

Wolfgang Härdle and Byeong Park
Additional contact information
Wolfgang Härdle: CORE, Université catholique de Louvain, B-1348 Louvain-la-Neuve, Belgium
Byeong Park: CORE, Université catholique de Louvain, B-1348 Louvain-la-Neuve, Belgium

No 1992024, LIDAM Discussion Papers CORE from Université catholique de Louvain, Center for Operations Research and Econometrics (CORE)

Abstract: Increasing dispersion in regression analysis means that with positive changes of the explanatory variable the residual variance increases. Motivated by theoretical questions in stability of demand systems we consider the question of increasing dispersion in a nonparameteric way. It amounts to testing the positive definiteness of differences of covariance matrices. The asymptotic distribution of the smallest eigenvalue of this difference is rather complicated that is why we also apply bootstrapping. The proposed method is applied to family expenditure data from the United Kingdom.

JEL-codes: G20 G35 (search for similar items in EconPapers)
Date: 1992-04-01
References: Add references at CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://sites.uclouvain.be/core/publications/coredp/coredp1992.html (text/html)

Related works:
Working Paper: Testing increasing dispersion (1994)
Working Paper: Testing increasing dispersion
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:cor:louvco:1992024

Access Statistics for this paper

More papers in LIDAM Discussion Papers CORE from Université catholique de Louvain, Center for Operations Research and Econometrics (CORE) Voie du Roman Pays 34, 1348 Louvain-la-Neuve (Belgium). Contact information at EDIRC.
Bibliographic data for series maintained by Alain GILLIS ().