Hi,
Use e(F) not r(F) and you will get the F statistic value. However, it seems that -regress- doesn't save the p-value. Have a look at the bottom of -help regress- to see which scalars are saved.
Probably there is a way to get it but i am not sure how.
Cheers
Manos
________________________________
From: [email protected] on behalf of Nuno
Sent: Tue 1/15/2008 10:57 PM
To: [email protected]
Subject: st: Problem with outreg2
Hi everyone,
I'm having a strage problem using -outreg2- and I was wondering if anyone
could give me a hand. I'm trying to output the result of a equation to a xml
file. I've used the following syntax, as described in outreg2 help file
(example 6):
clear
sysuse auto
regress mpg foreign weight length
test foreign weight length
outreg2 using auto5, addstat(Adjusted R-squared, e(r2_a), F test,r(F),Prob >
F, r(p)) tstat excel replace
I obtain the following output:
COEFFICIENT mpg
foreign -1.708
(-1.60)
weight -0.00437***
(-2.73)
length -0.0827
(-1.51)
Constant 50.54***
(8.09)
Observations 74
R-squared 0.67
Adjusted R-squared 0.659
F test
Prob > F
Although I'm able to get the "Adjusted R-squared" additional statistic in
the output file, the "F test" (r(F)) and "Prob>F" (r(p)) do not appear in
the output. If I use e(F), I'm able to get the F-stat, however I'm still
unable to input the probability of the F-Stat using the r(p). This is
strange as I can still access the values on r()... Any idea?
Best,
Nuno
*
* 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/
<<winmail.dat>>
