Re: st: cancel a selection and continue working with all thevariables or category of a variable

[Michael McCulloch <mm@pinest.org>]

Maarten,
In your strategy 2,
	gen byte touse96 = yearfile == "1996"
	reg y x if touse96 /// regression on selection
	reg y x            /// regression on complete file
what if you wanted to add a second level of selection, for example 
only children during 1996?
Can the command
	gen byte touse96 = yearfile == "1996"
be written like this:?
	gen byte touse96 = yearfile == "1996" & child==1
Michael




> --- carmen gamarra <carmengamarra@hotmail.com> wrote:
> >  I know how I would like to cancel a selection and continue working
> >  with all the variables or category of a variable?
> >
> >  Example:                     keep if  yearfile=="1996"
> >
> >  and then (cancel select)   cancel the selection and working with all
> >  the categories:
> -keep if expression- means you throw away everything for which
> expression is false. Once you throw it away, it is gone forever (unless
> you follow strategy 1 below).
>
> There are two strategies you can follow:
> 1)
> preserve
> keep if yearfile == "1996"
> reg y x /// regression on selection
> restore
> reg y x /// regression on complete file
>
> 2)
> gen byte touse96 = yearfile == "1996"
> reg y x if touse96 /// regression on selection
> reg y x            /// regression on complete file
>
> see -help preserve- for more on strategy 1, and -help if- for more on
> strategy 2. In most cases I would prefer strategy 2.
>
> Hope this helps,
> Maarten
>
>
> -----------------------------------------
> Maarten L. Buis
> Department of Social Research Methodology
> Vrije Universiteit Amsterdam
> Boelelaan 1081
> 1081 HV Amsterdam
> The Netherlands
>
> visiting address:
> Buitenveldertselaan 3 (Metropolitan), room Z434
>
> +31 20 5986715
>
> http://home.fsw.vu.nl/m.buis/
> -----------------------------------------
>
>
>      
> *
> *   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/