On Jun 15, 2004, at 2:33 AM, Clive wrote:
However, I noticed something in my two 'identical' models:
. areg edconch edround2 edround3 edtime edtimesq edyear edpollch
lagconch
laglabch lagldmch clmargin ldmargin conplace edenp class if
edmarker==1,
absorb(pano)
Number of obs = 1632
F( 14, 1314) = 69.42
Prob > F = 0.0000
R-squared = 0.7324
Adj R-squared = 0.6678
Root MSE = 6.1165
[...]
. tsset pano edyear
. xtreg edconch edround2 edround3 edtime edtimesq edyear edpollch
lagconch
laglabch lagldmch clmargin ldmargin conplace edenp class if
edmarker==1,
fe
Fixed-effects (within) regression Number of obs =
1632
Group variable (i): pano Number of groups =
304
R-sq: within = 0.4252 Obs per group: min =
1
between = 0.4157 avg =
5.4
overall = 0.3644 max =
10
F(14,1314) =
69.42
corr(u_i, Xb) = -0.5123 Prob > F =
0.0000
[...]
Now, I have fit the same models here (with the same FE in both) whilst
'switching off' any weighting and cluster options in both of them. How
is
it that the R^2 is not the same in both models? Doubtless I'm
overlooking
something. Ta.
Without looking carefully at the formulas used in xtreg, fe, I think
conceptually the issue is that xtreg, fe considers the explanation of
\sum {{y_{it} - \bar{y}_i)^2} : that is, after demeaning the data by
the individual means, how much of the remaining variation is explained
by your regressors? In areg, I suspect that in absorbing the factor
pano, the amount of variation absorbed is also included in r^2, just as
it would be if you included the dummies explicitly. That is, a one-way
ANOVA of your depvar on pano would explain some amount of the
variation. Do an ANOCOVA including pano and a bunch of regressors, and
you explain more. But the xtreg, fe model considers that the only thing
to be explained is y net of individual mean y.
Kit
*
* 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/
