Dear Statalisters,
For my thesis i’m using a panel-dataset.
I’d like estimate the effect of x1 ond y with -xtreg-. Since x2 is highly correlated with y and x1 the measured effect by excluding x2 would be spurious correlation. I tried to correct multicollinearity by differencing. But afterwards the linearity is not given anymore.
Is there any possibility to estimate the model by extracting the effect of x2?
Regards,
Luiz
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/faqs/resources/statalist-faq/
* http://www.ats.ucla.edu/stat/stata/
