Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
| From | Nick Cox <njcoxstata@gmail.com> |
| To | statalist@hsphsun2.harvard.edu |
| Subject | Re: st: Inverse Cummulative Variable |
| Date | Sun, 11 Mar 2012 12:42:26 +0000 |
Specifically, however, you want frequencies >= value. Best to negate your variable before calling -cumul-: gen work = -employees cumul work , gen(freq) freq equal tabdisp employees, c(freq) drop work Note that what you want is more commonly called the reverse, converse or complementary cumulative frequency. Calling it "inverse" runs a big risk of confusion with the quantile function. Nick On Sun, Mar 11, 2012 at 12:30 PM, Nick Cox <njcoxstata@gmail.com> wrote: > The -cumul- command is devoted to this question. > > For corresponding graphs, see -distplot- (SJ). On Sun, Mar 11, 2012 at 12:05 PM, Arantxa Crespo Rodriguez <acrodrig@eco.uc3m.es> wrote: > >> I have a dataset of firms with the number of employees for each one. >> I wanna create a variable that tells me how many firms have more or >> the same number of employees than the current observation. >> Example: >> >> Firm id Employees Inverse Cumulative >> 101 10 9 >> 102 20 8 >> 103 20 8 >> 104 37 6 >> 105 38 5 >> 106 52 4 >> 107 52 4 >> 108 52 4 >> 109 60 1 * * 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/