Re: st: generating a word table including the first stage regression(s) with an iv-regression

[Eric Booth <ebooth@ppri.tamu.edu>]

<>

Also, it doesn't affect the output in this case, but you can remove the "margin" option from the -estout- line unless you've run them (which, as the -estout- help files mentions, when used  "with multiple-equation models can be tricky")

- Eric

__
Eric A. Booth
Public Policy Research Institute
Texas A&M University
ebooth@ppri.tamu.edu
Office: +979.845.6754

On Dec 7, 2010, at 11:04 AM, Eric Booth wrote:

> <>
> 
> Also, note that if you remove the "vce(cluster id) " from the -ivregress- statement, then the first stage in the -ivregress- matches the output for the -regress-
> - 
> - Eric
> 
> __
> Eric A. Booth
> Public Policy Research Institute
> Texas A&M University
> ebooth@ppri.tamu.edu
> Office: +979.845.6754
> 
> 
> On Dec 7, 2010, at 10:53 AM, Eric Booth wrote:
> 
>> <>
>> 
>> This is close, but the 1st stage in the -ivregress- is slightly different than the standalone -regress-  I'm not sure if it's possible to manipulate the -regress- to match the first stage in -ivregress- :
>> 
>> *********!
>> 
>> webuse hsng2, clear
>> g id = state
>> 
>> regress hsngval pcturban faminc, 
>> est sto one
>> ivregress 2sls rent pcturban (hsngval = faminc), vce(cluster id) first
>> est sto two
>> 
>> outreg2 [one two] using test.doc, replace bdec(2) bfmt(f) sdec(7) sfmt(e)
>> 
>> **or using -estout- :
>> estout one two,  cells(b se(par)) margin legend
>> 
>> *********!
>> 
>> - Eric
>> __
>> Eric A. Booth
>> Public Policy Research Institute
>> Texas A&M University
>> ebooth@ppri.tamu.edu
>> Office: +979.845.6754
>> 
>> 


*
*   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/