Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
st: Testing for Serial Correlation in Panel Data (while using time lags)
From
Christopher Parker <[email protected]>
To
[email protected]
Subject
st: Testing for Serial Correlation in Panel Data (while using time lags)
Date
Fri, 7 Mar 2014 01:50:41 +0100
Dear Statalists,
I'm searching for ways to test for serial correlation in Panel data.
More specifically my dependent variable is first differenced (to avoid
serial correlation) and some of my explanatory variables are lagged.
One of the first solutions I found is the -xtserial- command. As it
does not allow time series operators I created lagged variables (gen
lx=l.x) before conducting the test and the results were fine. Is there
a theoretical reason why time operators are not allowed or should my
test results be reliable? (In my opinion: no, there is not.)
What are the alternatives to the -xtserial- command in order to test
for serial correlation with stata?
Many thanks ahead,
Chris
*
* 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/