# values less + (1/2) # values same
-----------------------------------
# values
which boils down to various -count-s. See also -cumul-.
Nick
[email protected]
Eric G. Wruck
> I ran a <summ days, de> on the variable days & of course obtained the
> 25th & 50th percentiles (among others). My 25th percentile was close
> to zero days & my median 4 days. Is there a way to obtain the
> percentiles corresponding to say 1, 2, & 3 days? I know I can
> compute percentiles using the pctile command so I could pick a fine
> setting & then search for the closest to the values I am interested
> in but that seems rather kludgy -- is there another way?
*
* 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/
