Statalist


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

R: st: R: Kaplan meier graphs


From   "Carlo Lazzaro" <[email protected]>
To   <[email protected]>
Subject   R: st: R: Kaplan meier graphs
Date   Thu, 5 Feb 2009 14:06:56 +0100

Dear Sarah,
taking a look at Stata manual release 9 (Volume Survival analysis and
epidemiological tables: 269-272) it seems that you can adjust your KM
estimates for more variables at the same time.
Please, see example below (Stata 9.2/SE):
---------------------begin example--------------------------------------
sysuse cancer.dta
(Patient Survival in Drug Trial)
save "C:\Documents and Settings\carlo\Desktop\sarah.dta"
stset studytime, failure(died)
g alfa=1 if died ==0
replace alfa =0 if alfa ==.
sts graph, by(drug) adjustfor( alfa age)
----------------------end example----------------------------------------

HTH and Kind Regards,
Carlo
-----Messaggio originale-----
Da: [email protected]
[mailto:[email protected]] Per conto di sarah keys
Inviato: giovedì 5 febbraio 2009 13.26
A: [email protected]
Oggetto: Re: st: R: Kaplan meier graphs

Thanks Carlo - that worked!

I don't suppose you (or anyone else) know about adjusting KM?
I am not even sure if it make sense to adjust survival functions?

I can adjust by one factor i.e: age shown below:

sts,by(group) fail adjustfor(age) ylabel(0 0.1 0.25) tmax(2)

but what about for multiple factors - can't get the coding right

Really appreciate this help as I am a newy!

Many thanks

Sarah


On Thu, Feb 5, 2009 at 12:26 PM, Carlo Lazzaro
<[email protected]> wrote:
> Dear Sarah,
> as far as
> <How do I cut off KM at, say, 4 years follow-up ?>
> Try (Stata 9/2 SE)
> - sts graph, tmax(4)-
>
> HTH and Kind Regards,
> Carlo
>
> -----Messaggio originale-----
> Da: [email protected]
> [mailto:[email protected]] Per conto di sarah keys
> Inviato: giovedì 5 febbraio 2009 10.51
> A: [email protected]
> Oggetto: st: Kaplan meier graphs
>
> Kaplan meier graphs
>
> I am using a multiple record data set. and have Stset as below:
>
> stset date_visit if chc!="", enter(all) fail(chcstop) id(client_id)
> origin(startn)scale(365.25)
>
> *** and had the final cox model:
> xi: stcox i.group age bffa i.w50s
>
> I produced KM graph with the following commands:
>
> sts,by(group) fail ylabel(0 0.05 0.1) risktable
> graph export chc.emf, replace
>
>
> My questions are:
> Can I adjust the KM in the same way as the COX model (adjust by age
> bffa i.w50s)to compare group 1 and group 2?
> How do I cut off KM at, say, 4 years follow-up ?
> Thanks for help
> Sarah
> *
> *   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/
>
>
>
> *
> *   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/
>

*
*   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/



*
*   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 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index