Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

RE: st: Comparison of two or more observations


From   "Nick Cox" <n.j.cox@durham.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   RE: st: Comparison of two or more observations
Date   Wed, 19 Oct 2005 17:30:48 +0100

-duplicates- is in part designed for this 
very purpose!  

Nick 
n.j.cox@durham.ac.uk 

Philipp Rehm
 
> You could do this:
> 
> collapse (sd) fvc fev1, by(patid)
> 
> /* this calculates the standard deviation on each variable of 
> interest 
> for each patient. Clearly, you want the standard deviation to 
> be zero */
> 
> drop if fvc==0 & fev1==0
> 
> /* this drops all observations with identical entries and leaves only 
> partients in the data-set with mistyped data (assuming, of 
> course, that 
> the data have not been mistyped twice */

Philip Ryan 

> > Separate your data set into two and use Tom Steichen's 
> -cf3- program, available
> > using -ssc-

Seb Buechte

> >>we have been entering lung function data over the course of the last
> >>few month. To be able to identify mistyped data we have entered all
> >>data twice. So for a patient who received a lung function 
> measurement
> >>on 12 Jan 2002 I have two observation holding all the data 
> gained from
> >>that measurement.
> >>
> >>I am now wondering wether there is an easy way to compare those two
> >>observations? The data could look like this
> >>
> >>patid	lufudate	fvc	fev1
> >>1	10jan2002	5.1	4.8
> >>1	10jan2002	5.1	4.3
> >>2	09jan2002	4.3	3.7
> >>2	09jan2002	4.3	3.7
> >>3	08jan2002	2.9	2.6
> >>3	08jan2002	2.9	6.2
> >>
> >>(This is articial data that I just made up. The "real" data contains
> >>approx. 20 parameters)
> >>
> >>So is there any program out there that would help me with this task?

*
*   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/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index