Statalist


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

Re: st: stcompet


From   "enzo.coviello@tin.it" <enzo.coviello@tin.it>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: stcompet
Date   Tue, 4 Nov 2008 09:13:48 +0100 (GMT+01:00)

Hugh Robinson ha scritto:
> I'm trying to determine cause specific 
mortality rates from encounter
> data (133 individuals, 17000 rows, 6 
possible causes of mortality).  
> The data is StSet as: 
>
> "stset 
date1, id(lion_id) failure(fatecode==1) enter(event==1) origin
> (time d
(01Jan1998)) exit(time d(01Jan2007))"
>
> When I ask stcompet to 
calculate the cumulative incidence using
> "stcompet CumInt = ci, 
compet1(2) compet2(3)",
>
> STATA creates the new variable I stipulate, 
but then simply adds a 0 to
> each row when a mortality occurred, all 
other rows are no data ".".
>
Dear Hugh,

the output of -stset- could 
add some suggestion about what happens when -stcompet- is used to 
generate the cumulative incidence function.

Anyway, I would be pleased 
to give some further insight to your problem.
To this aim you should 
send me privately a part of your data set and do file.

When the 
problem has been resolved, we may send a mail to the List whit more 
detailed comments.

Best wishes.

Enzo



 


^^^^^^^^^^^^^^^^
Enzo Coviello
Unita' di Statistica ed Epidemiologia ASL BARI
piazza Vittorio Emanuele, 14
70054 - GIOVINAZZO (BA)
Italy
tel. fax +39 080 3357883
tel (home) +39 0883 695055
mobile 347 5016016

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   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