Dear stata list,
I have a query regarding the 'xtserial' test for serial correlation (Drukker, 2003)**. I have noted that some others have asked what to do if this test reports "no observations" but there does not seem to be any consensus on how to handle this. The syntax I typed is:
. xtreg sq_personASR ilog_fert ilog_div ilog_migrant iruralpop miss_index_m_ecog miss_index_2socialmovecontact miss_develop_ivare_gindex, re
. xtserial sq_personASR ilog_fert ilog_div ilog_migrant iruralpop miss_index_m_ecog miss_index_2socialmovecontact miss_develop_ivare_gindex
no observations
r(2000);
The data I am using is an unbalanced panel data set and has been ‘xtset’. None of the variables specified above are in string format but there is missing data.
I note that other have said that there is a problem with xtserial and unbalanced time periods but how can this be fixed?
Any help would be great.
Thanks, Allison
** xtserial implements a test for serial correlation in the idiosyncratic errors of a linear
panel-data model discussed by Wooldridge (2002). Drukker (2003) presents simulation evidence
that this test has good size and power properties in reasonable sample sizes. Under the null of no serial the residuals from the regression of the first-differenced variables should have an autocorrelation of -.5. This implies that the coefficient on the lagged residuals in a regression of the lagged residuals on the current residuals should be -.5. xtserial performs a Wald test of this hypothesis. See Drukker (2003) and Wooldridge (2002) for further details.
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
