Exploiting Cross Section Variation for Unit Root Inference in Dynamic Data
This paper considers unit root regressions in data having simultaneously extensive cross section and time-eries variation. The standard least squares estimators in such data structures turn out to have an asymptotic distribution that is neither Dickey-Fuller, nor normal and asymptotically unbiased. Instead, the estimator turns out to be consistent and asymptotically normal, but has a nonvanishing bias in its asymptotic distribution.
When requesting a correction, please mention this item's handle: RePEc:fmg:fmgdps:dp171. See general information about how to correct material in RePEc.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (The FMG Administration)
If references are entirely missing, you can add them using this form.