As others have implied, you should not -drop- such observations as they
contain information.
Ziad El-Khatib
But what to do if patients have been censored, i.e. they had event==0
at last observation?
On Jan 23, 2008 1:21 PM, Nick Cox <[email protected]> wrote:
> Without knowing this is biostatistically sensible for your problem,
>
> . keep if event == 1
>
> is one Stata answer for your question.
>
> -----Original Message-----
> From: [email protected]
> [mailto:[email protected]] On Behalf Of Ziad
> El-Khatib
> Sent: 23 January 2008 20:59
> To: [email protected]
> Subject: st: Arranging dataset for KM survival rate
>
> Hey again
> I am trying to arrange my dataset to keep one record that has the
> failure event or censor data per patient.
> Any tips about command how to delete the other records prior to
> failure/censor record per patient?
>
> For example
>
> Record nbre ID Time Event
> 1 1001 1 0
> 2 1001 2 0
> 3 1001 3 1
> 4 1002 1 0
> 5 1002 2 1
>
>
> How to be able to take away lines 1,2 and 4?
*
* 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/
