<>
I could say in my defence that you asked for the count of observations and
the observations themselves, and I gave you exactly that. Your subject line
asked for the nobs, and the text for " the observations used in my -3reg-
estimation". -list- and -count- are the ways to achieve these goals...
Still, how about missings values for a start? Could they be the cause of
your problem? Just type -inspect- to see whether there are missings in any
of your data...
HTH
Martin
-----Ursprüngliche Nachricht-----
Von: [email protected]
[mailto:[email protected]] Im Auftrag von Wiebke
Schlanbusch
Gesendet: Freitag, 25. September 2009 15:22
An: [email protected]
Betreff: Re: st: AW: Number of observations
Aaah, sorry I made a mistake... I do use -reg3- Thank you, Martin.
I tried both of your suggestions, but they offer me only the numbers of
observations included in the 3SLS-Estimation (count if e(sample)) or offer
me a list of all observations and the value of the variables (list if
e(sample)). Unfortunately non of your suggestions can explain why Stata
isn't using all the observations in the data sheet.
Thank you very much for you help. It really is appreciated.
Wiebke
----- Original Message ----
From: Martin Weiss <[email protected]>
To: [email protected]
Sent: Friday, September 25, 2009 2:51:49 PM
Subject: st: AW: Number of observations
<>
Is it -3reg- or -reg3-? I hope: the latter. Just say
*************
count if e(sample)
*************
to find the number of obs...
You could also -list if e(sample)- though this will give you lots of
output...
HTH
Martin
-----Ursprüngliche Nachricht-----
Von: [email protected]
[mailto:[email protected]] Im Auftrag von Wiebke
Schlanbusch
Gesendet: Freitag, 25. September 2009 14:51
An: [email protected]
Betreff: st: Number of observations
Dear Statalist'ers,
does anyone of you know a way to make Stata 10.1 show the observations used
in my -3reg- estimation? My data sheet contains more than 30,000 cases but
Stata uses only about 5,000 of these. I assume this dropping of observations
to be a reason the "R-squared" offered by -reg3- differs so much from my
pseudo-R².
Kind regards,
Wiebke
*
* 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/
*
* 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/
