ROBERT BOZICK wrote:
> I am working on recoding a categorical variable (orig) with 10 values into
> a binary variable (origred) coded 0,1.
>
> gen origred = .
> replace origred = 0 if orig >=1 & orig <=5
> replace origred = 1 if orig >5 & orig <=10
>
> There are a number of missing values for the original variable orig.
>
> Is there a way to have Stata randomly assign those missing values to either
> a 0 or a 1 in the new variable origred? I am completely stumped.
You can add the line
replace origred = floor(uniform()*2) if mi(orig)
to the commands above.
You can also replace all your commands by a one-liner:
gen origred = cond(mi(orig),floor(uniform()*2,inrange(orig,6,10))
Uli
--
Ulrich Kohler
[email protected]
030/25491-361
*
* 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/
