Exploiting Cross Section Variation for Unit Root Inference in Dynamic Data
1993 (English)Report (Other academic)
This paper considers unit root regressions in data having simultaneously extensive cross-section and time-series variation. The standard least squares estimators in such data structures turn out to have an asymptotic distribution that is neither Op(T-1) Dickey-Fuller, nor Op(N-1/2) normal and symptotically unbiased. instead, the estimator turns out to be consistent and asymptotically normalm, but has a nonvanishing bias in its asymptotic distribution.
Place, publisher, year, edition, pages
Stockholm: IIES , 1993. , 22 p.
Seminar Paper / Institute for International Economic Studies, Stockholm University, ISSN 0347-8769 ; 549
random field, time series, panel data, unit root
IdentifiersURN: urn:nbn:se:su:diva-41868OAI: oai:DiVA.org:su-41868DiVA: diva2:338063
Published in connection with a visit at the IIES.2010-08-102010-08-102010-08-10