Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, is already up and running.

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: Counting a population given start/end times

From   Scott Simpson <>
Subject   st: Counting a population given start/end times
Date   Sat, 3 Nov 2012 12:51:20 -0700 (PDT)

Hi all-
First time posting, any help appreciated.

I have a data set that lists patients' clinic visits.  Given each inidividual's time into the clinica and time out of the clinic, I am trying to create a variable that tells me how many patients are in the clinic at a given time.  In essence, the clinic population at a given point in time, really, the clinic population at the point the patient arrives.

I thought I had it by counting the # of pts who had arrived before, then substracting those who left before--

sort DateandTimeIN;
gen inorder = _n;
gen inbefore = inorder - 1;
sort DateandTimeOUT;
gen outorder = _n if !missing(DateandTimeOUT);
gen leftbefore = outorder - 1;
sort DateandTimeIN;
gen currentpop = inbefore + 1 - leftbefore;

(Admittedly, there are some unaccounted patients already in clinic before my data starts, will have to manually figure that out and correct.)  The output of the above, however, gives me a lot of negative numbers for currentpop, which does not make intuitive sense to me unless the recorded time is incorrect.

This seems as though would be a common programming question but am not finding answers among local experts or online.  Must be a .do file out there for this?


Scott Simpson MD MPH
University of Washington School of Medicine
Seattle, WA

*   For searches and help try:

© Copyright 1996–2016 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index