<>
In a way, the message is true, as the "e(b)" and "e(V)" are indeed not
there. Still, could this be due to different versions of -esttab- present on
your machines? What does -which esttab- give you on each machine?
HTH
Martin
-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of Bert Jung
Sent: Montag, 21. September 2009 00:22
To: [email protected]
Subject: st: -esttab- runs on Windows but on Unix says "list estimation
result do not have e(b) and e(V)"
Dear Statalisters,
I am using -estpost- and -esttab-. On my Windows system the -estpost-
example code works fine. But on a Unix server (my datasets are very
large) I get an error message "list estimation result do not have e(b)
and e(V)" although -ereturn list- shows that the matrices are
available. Any suggestions on how to adapt the fantasticly useful
-estout- code would be much appreciated.
Thanks as always,
Bert
* Output from Unix system using the -estpost- example code from
http://repec.org/bocode/e/estout/estpost.html#estpost102
. sysuse auto, clear
(1978 Automobile Data)
. estpost tabstat price mpg rep78, listwise statistics(mean sd)
Summary statistics: mean sd
for variables: price mpg rep78
| e(price) e(mpg) e(rep78)
-------------+---------------------------------
mean | 6146.043 21.28986 3.405797
sd | 2912.44 5.866408 .9899323
. esttab, cells("price mpg rep78") nomtitle nonumber
list estimation result do not have e(b) and e(V)
r(321);
. ereturn list
scalars:
e(N) = 69
macros:
e(cmd) : "estpost"
e(subcmd) : "tabstat"
e(stats) : "mean sd"
e(vars) : "price mpg rep78"
matrices:
e(price) : 1 x 2
e(mpg) : 1 x 2
e(rep78) : 1 x 2
*
* 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/
*
* 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/
