Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
| From | Scott Merryman <scott.merryman@gmail.com> |
| To | statalist@hsphsun2.harvard.edu |
| Subject | Re: st: variable containing proportions of another variable |
| Date | Fri, 16 Nov 2012 16:37:16 -0600 |
clear input pid hid X proportion 1 1 0 0 2 1 0 0 3 1 0 0 4 2 1 0 5 2 0 1 6 3 0 1 7 3 1 0.66 8 3 1 0.66 9 3 1 0.66 10 4 0 0.4 11 4 0 0.4 12 4 0 0.4 13 4 1 0.2 14 4 1 0.2 15 4 0 0.4 end egen total = total(X), by(hid) bys hi: gen proportion2 = (total-X)/(_N-1) drop total l Scott On Fri, Nov 16, 2012 at 4:27 PM, Manos Mentzakis <mmentzakis@gmail.com> wrote: > Dear all, > > Apologies for the uninformative subject line but I couldnt think of a > way to easily describe my problem. I d like to create a variable that > takes as values the proportion of ones of another variable X when the > line under consideration is excluded. Specifically, I d like to have > the proportion of smokers in the household other than the individual > under consideration. Below is a table where proportion is the variable > I d like. pid is individual identifier, hid is household identifier, X > is an indicator with 1 if smoker 0 otherwise. > > pid hid X proportion > 1 1 0 0 > 2 1 0 0 > 3 1 0 0 > 4 2 1 0 > 5 2 0 1 > 6 3 0 1 > 7 3 1 0.66 > 8 3 1 0.66 > 9 3 1 0.66 > 10 4 0 0.4 > 11 4 0 0.4 > 12 4 0 0.4 > 13 4 1 0.2 > 14 4 1 0.2 > 15 4 0 0.4 > > > Any help is greatly appreciated. > > Regards > Manos > * > * For searches and help try: > * http://www.stata.com/help.cgi?search > * http://www.stata.com/support/faqs/resources/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/faqs/resources/statalist-faq/ * http://www.ats.ucla.edu/stat/stata/