----- Original Message -----
From: "You-Ta Chuang" <[email protected]>
To: <[email protected]>
Sent: Thursday, December 12, 2002 5:21 PM
Subject: st: Question about xtabond and xtreg
> Hi all,
>
> I am playing with the cross-sectional,time series data I have. I couldn't
quite
> figure out something here.
>
> When I used the xtreg, the result table showed
> Number of obs: 4248
> Number of groups: 246
>
> However, when I ran the xtabond (no additional specification, i.e., lag 1
only),
> the result table showed
> Number of obs: 3756
> Number of groups: 240
>
> I am not aware of any missing data in my sample. The time period is 19 yrs.
What
> I don't understand is why the numbers of obs and groups are so different
between
> xtreg and xtabond. I would appreciate it very much if someone could give me
some
> advise here. Thanks!
>
With xtabond, lags(1) the first two observations (per group) are lost due to
lags and differencing. I imagine that 6 of your groups only had two
observations so they would be lost plus 2 observations per group for the
remaining groups. Which will leave you with:
4248 - 2*240 - 2*6 = 3756.
Since xtreg does not difference the data or impose lags so no observations are
lost.
Scott
*
* 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/
