But what then is the status of the -xtserial- results? You need to
grapple with a new time metric, implicitly assumed comparable both
within and between panels.
Nick
[email protected]
Austin Nichols
Kenneth F <[email protected]> :
Make a new "time" variable that has no gaps:
bysort panelid (timeid): g faketime=_n
tsset panelid faketime
On Sat, Jul 19, 2008 at 9:18 PM, Greene, Kenneth F
<[email protected]> wrote:
> When I run xtserial I get the error "no observations." I have an
unbalanced panel with no missing values and my model uses the full
dataset (i.e., no "if" statement that excludes cases). The data are
country-election-year and thus the time observations are unequally
spaced across the panels and in some cases even within panels. My
intuition is that the problem may lie with tsset. I used "tsset year,
generic" because I'm not sure how to specify the type of data I have.
Any suggestions would be much appreciated.
*
* 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/
