Dear Fellow Listees,
I have tried to conduct unit root tests on the
dependent variable in a panel data set with
-levinlin-, but realized that using different values
for the "lag" option gives me different results as to
whether I could reject the null hypothesis of
nonstationarity. My question is thus: if my test
indicates that I cannot reject the null when lag=3
(but not if lag=2), how could I incorporate such
information (i.e. unit root is not a problem when
tested with lag=3) into eventual regression analyses?
Or, should I? Thanks so much!
Best,
yumin
__________________________________
Do you Yahoo!?
Yahoo! Hotjobs: Enter the "Signing Bonus" Sweepstakes
http://hotjobs.sweepstakes.yahoo.com/signingbonus
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
