If there are no duplicate or missing values, then either _N/2 or (_N-1)/2 will
be strictly above the median, depending on whether _N is even or odd,
respectively. If there are duplicate or missing values, then you'll have to
calculate the median to know how many are strictly above it.
I would only ever take the second route; it's not clear why calculating
and using the median would ever be a problem.
hth,
Jeph
Monika Huembelin wrote:
I'd like to calculate how many observations in each cohort are above the total median value of a variable. Does anyone know if there is an easy way to do that without having to calculate the median first and include the value in each following calculation? I couldn't find anything in the help files. Thank you
Monika
*
* 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/
*
* 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/
