Re: -nestreg- (was: st: saving a sample after a regression)

["Michael S. Hanson" <mshanson@mac.com>]

On Mar 12, 2007, at 4:40 PM, Jeff Pitblado, StataCorp LP wrote:

> Michael S. Hanson <mshanson@mac.com> expressed an interested in 
> getting -nestreg- to support a command:
>
>
> > The on-line help also makes reference to using -sw- or -swml- as 
> > -program- properties for the user-written program.... But neither the 
> > on-line help nor the manuals have turned up any information on such 
> > properties (although I concede I may have missed them).
> Program properties are documented in -[P] program properties-, which 
> is also present in the online help.  In Stata type
>
> 	. help program properties
	Thanks, Jeff.  I guessed I had probably missed them;  next time I'll 
look with -hsearch- instead of just using the "Find" command from the 
OS with a particular help file.  Trying -hsearch sw- now shows 
-program_properties- as the top hit.



> Note that the paretheses in -ivreg-'s varlist syntax are in conflict 
> with the standard syntax required by -nestreg-.  Here is a simple 
> wrap-around routine for -ivreg- that allows you to fix the 
> instrumental variables when it is prefixed with -nestreg-:
>
> 	program myivreg, prop(sw)
> 		version 9.2
> 		syntax [varlist] [if] [in] [aw fw iw pw] [, ivlist(string) *]
> 		ivreg `varlist' (`ivlist')			///
> 			`if' `in' [`weight'`exp'], `options'
> 	end
>
> In -myivreg-, all we really did was provide the standard syntax and 
> the -sw- program property; -ivreg- handles all the other things like 
> -e(b)-, -e(V)-, and -e(sample)-.
	Thanks also for that example -- it gives me something to experiment 
with.

                                        -- Mike

*
*   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/