[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
st: Re: statalist-digest V4 #1159
--On Saturday, February 15, 2003 2:33 -0500 Vincent wrote:
It surely will if you issue the tsset command, and specify a time variable
that can be interpreted in that date format. Stata's panel commands, going
back to pre-time series days, often allow you to specify only the i
variable with i() where knowledge of the t() is not needed. You have always
been able to define those two with iis and tis, or now together in tsset.
But if the time variable is not defined, various panel data estimators will
work, but will not be able to refer to the time index in calendar time in
an if tin.. clause.
I have a new question.
In Panel data, sometimes we want to estimate a shorter
time period than the time spans in the data set. It
seems to me that the "in" option does not work. What
can I do if I want to estimate say 1977:1 to 1998:10
with same number of groups while the time span is
1972:1 to 2002:12 in the data set.
Christopher F Baum, Boston College Economics, Chestnut Hill MA 02467 USA
* For searches and help try: