Scott Merryman wrote:
> These commands can only be used with time-series data not panel data,
> however,
> take a look at Kit Baum's "panelauto" module which supports tests for
> autocorrelation on panel data.
Cheers. I actually managed to sort it out before getting back to the list,
so apologies for that. What I was doing wrong, of course - as you rightly
point out - was
. tsset panelvar timevar
when it ought to have been
. tsset timevar
After that, it was plain sailing. Thanks to Diego (<guest g2int>), I have
located -panelauto-, looked at its contents and I want to download it.
Diego remarked on Thursday that he's noticed that using autocorrelation
test _after running_ -xtgls- are all showing highly significant
autocorrelation. I share his bewilderment (-xtgls- is meant to be good at
_correcting_ for it!), so -panelauto- could be useful in this regard.
Unfortuantely, I'm not yet in a position to download packages online to my
Stata at present, for reasons I shan't bore you with.
CLIVE NICHOLAS |t: 0(44)191 222 5969
Politics Building |e: [email protected]
School of Geography, |f: 0(44)870 126 2421
Politics & Sociology |
University of |
Newcastle-upon-Tyne |
Newcastle-upon-Tyne |
NE1 7RU |
United Kingdom |http://www.ncl.ac.uk/geps
*
* 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/
