Saturday, June 2, 2012

Panel Unit Root Tests

Testing for unit roots in panel data is pretty standard stuff these days. Any decent econometrics package has everything set up to make life easy for practitioners who want to apply such tests. As usual, though, ease of application doesn't guarantee correct application of the tests, or the interpretation of the associated results.


So, I was interested to read a paper by Hashem Pesaran, titled "On the Interpretation of Panel Unit Root Tests". The paper is "forthcoming" in Economics Letters, and was recently made available on that journal's website. Hashem has contributed as much (if not more) than anyone to the literature on panel unit roots tests, so I take his work and views very seriously.

This short paper of his is well worth reading. Let me quote the Abstract to give to the take-away message:
"Applications of panel unit root tests have become commonplace in empirical economics, yet there are ambiguities as how best to interpret the test results. This note clari es that rejection of the panel unit root hypothesis should be interpreted as evidence that a statistically signi cant proportion of the units are stationary. Accordingly, in the event of a rejection, and in applications where the time dimension of the panel is relatively large, it recommends the test outcome to be augmented with an estimate of the proportion of the cross-section units for which the individual unit root tests are rejected. The economic importance of the rejection can be measured by the magnitude of this proportion."
Reference:

Pesaran, M. H., 2012. On the interpretation of panel unit root tests. Economics Letters, forthcoming.

(A much, much earlier version of the paper can be found here.)
(A WP version can be found here.  Thanks, Eric - see comment below!)

© 2012, David E. Giles

2 comments:

  1. And a very recent version can be found here:
    http://www.econ.cam.ac.uk/faculty/pesaran/wp11/Interpretation-Panel-Unit-September-2011.pdf

    ReplyDelete

Note: Only a member of this blog may post a comment.