Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
st: RE: post estimation tests with areg
From
"Martin Weiss" <[email protected]>
To
<[email protected]>
Subject
st: RE: post estimation tests with areg
Date
Tue, 21 Sep 2010 19:46:39 +0200
<>
One obvious issue: The type of -predict-ion you want must be specified as an
option. Otherwise Stata thinks you want a -varname- "xb" and another
-varname-, which would be one too much...
*************
sysuse auto, clear
areg mpg weight gear_ratio, absorb(rep78)
predict yhat, xb
predict residual, res
*************
HTH
Martin
-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of Benhoen2
Sent: Dienstag, 21. September 2010 19:15
To: [email protected]
Subject: st: post estimation tests with areg
Hello Stata-listers,
I am a novice Stata user (of 2 weeks) with more questions than answers. I
am using the areg command to efficiently control for ~2000 fixed effects
variables in a regression that has 3-7 independent variables for ~ 110,000
cases. Although the regression itself is very useful (and very fast), I
have been unsuccessful at finding a way to do the following post-estimation
activities:
1) save predicted values and residuals: I have tried using predict xp
[varname] and predict r [varname], respectively. Both generate the following
error, "too many variables specified"
2) save standardized residuals (Though if I had un-standardized residuals I
could calculate myself)
3) test for heteroskedasticity
4) produce VIF statistics among IV, and
5) produce leverage statistics
...essentially many of the post-estimation options from regress. Are there
any programs out there to produce these? (A SSC search was unsuccessful)
Should I be using another regress command entirely? Is regress the only way
to get there?
If it turns out that regress is the only way to handle this, any advice on
a) how to efficiently create the 2000 fixed effects variables, and b)
encourage the most efficient use of regress with these variables.
Thanks, in advance, for any and all.
Ben
Berkeley Lab
*
* 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/