> -----Original Message-----
> From: [email protected] [mailto:owner-
> [email protected]] On Behalf Of Hoetker, Glenn
> Sent: Friday, December 17, 2004 3:00 PM
> To: [email protected]
> Subject: st: first stage regressions in ivreg. Problems and using outreg,
> etc.
>
> Hi all and help please.
>
> I'm running ivreg and want to include the first stage regression in my
> output via outreg, mktab, or a similar program.
>
> From Statalist, there appears to be no pre-packaged way to do so.
> However, one alternative that was suggested was to run the first-stage
> regression by itself and use that output in outreg, mktab, whatever.
> Not perfect, but better than doing it entirely by hand.
>
> However, when I try to do this, I find that my manually run first-stage
> regression doesn't match was Stata reports when doing the ivreg. I've
> made sure I'm running the command on the same sample. (See below).
>
<snip>
Glenn,
You only report the same variables are being used, but are you sure it is
over the same sample. If you dependent variable "common_action_new_pc" has
any missing observations than sample for the first stage will be restricted.
For example, compare the first stage results from -ivreg- to -reg- in the
following cases:
Case 1.
sysuse auto
ivreg price mpg (weight = length), first
reg weight mpg length
Case 2.
replace price = . in 1/5
ivreg price mpg (weight = length), first
reg weight mpg length
Scott
*
* 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/
