Re: st: Recoding missing variables

[Richard Williams <Richard.A.Williams.5@ND.edu>]

At 09:44 AM 7/16/2006, David Kantor wrote:

> This is probably what you had in mind, but this has the slight 
> "problem" that as you tweak your covariate set, the observation set 
> may change as well.
If you want to make sure you are analyzing the same cases throughout, 
you can do something like

gen touse = !missing(y1, y2, x1, x2, x3, x4)
reg y1 x1 x2 x3 if touse
reg y2 x2 x3 x4 if touse

The variable touse will be coded 1 for those cases with no missing 
data, 0 otherwise.

Incidentally, we are talking about listwise deletion of missing data 
here.  That is probably the most common and as good or better as many 
of the suggested alternatives.  But, if you want to get a little 
fancier, check out -findit ice- or maybe some of the other routines 
that show up when you type -findit impute-. I'd like to see Stata 
come up with some more built-in utilities of its own rather than have 
the burden mostly fall to user-written routines.



-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
FAX:    (574)288-4373
HOME:   (574)289-5227
EMAIL:  Richard.A.Williams.5@ND.Edu
WWW (personal):    http://www.nd.edu/~rwilliam
WWW (department):    http://www.nd.edu/~soc 
*
*   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/