Hi
I am working with panel data. I have used drukker test and found serial
correlation. I am confused whether I can use newey2 to solve the problem since
it is fixed effect model. I found in the web (reply to a question) that it is
possible with a command like this xi: newey2 y x1 x2 i.fe xk, lag(#) force.
But as I found, it does not work.
Another way is arellano-bond estimation. In my model, the dependent variable
is tax-GDP ratio and independent variables are: agriculture value-added (%of
GDP), industry value-added (% of GDP), International trade-GDP ratio, debt-GDP
ratio, population growth rate, GDP per capita. Can I use Arellano-Bond
estimation in my model?
Can I solve the serial correlation problem within fixed effect model?
I am also confused about the degree of serial correlation in drukker test.
Does it mean that there is first-order correlation or a higher degree? What
should I put in lag (#) option in newey2 command?
I am looking forward for your help. Thank you very much in advance.
Sincerely,
Sams Uddin Ahmed
Bangladesh
[email protected]
-------------------------------------------------
This mail sent through AITL WEB MAIL SERVICE
*
* 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/
