Re: R: st: Is there a similar command as roccomp for comparing two kaplan-meier curves?

[Steve Samuels <sjsamuels@gmail.com>]

I was just writing to suggest -somersd- when Roger's post appeared in my
mailbox.  I'll just add that the command's -cluster()- option will account 
for the presence of individuals in both curves. 

Steve

On Oct 8, 2012, at 9:04 AM, Roger B. Newson wrote:

One possibility here is to use the -somersd- package, downloadable from SSC, to compute a confidence interval and a P-value for the Gehan–Breslow–Wilcoxon Somers' D of survival time with respect to membership of Group 1 instead of Group 2. This practice is demonstrated in Subsection 5.2 of Newson (2006), which you can download free from the Stata Journal website at

http://www.stata-journal.com/article.html?article=snp15_6

I hope this helps. Let me know if you have any further queries.

Best wishes

Roger


References

Newson R. Confidence intervals for rank statistics: Somers' D and extensions. The Stata Journal 2006; 6(3): 309-334.

Roger B Newson BSc MSc DPhil
Lecturer in Medical Statistics
Respiratory Epidemiology and Public Health Group
National Heart and Lung Institute
Imperial College London
Royal Brompton Campus
Room 33, Emmanuel Kaye Building
1B Manresa Road
London SW3 6LR
UNITED KINGDOM
Tel: +44 (0)20 7352 8121 ext 3381
Fax: +44 (0)20 7351 8322
Email: r.newson@imperial.ac.uk
Web page: http://www.imperial.ac.uk/nhli/r.newson/
Departmental Web page:
http://www1.imperial.ac.uk/medicine/about/divisions/nhli/respiration/popgenetics/reph/

Opinions expressed are those of the author, not of the institution.

On 08/10/2012 09:43, Carlo Lazzaro wrote:
> Dear Ton,
> what follows might be of some help:
> --------------------------------------------------------------
> use http://www.stata-press.com/data/r12/stan3
> g A=2 if surgery==1 & transplant==1
> replace A=1 if surgery==0 & transplant==1
> replace A=0 if surgery==0 & transplant==0
> sts graph, by(A)
> sts test A, logrank
> --------------------------------------------------------------
> 
> Take a look at - help sts test - for further details.
> 
> Kindest Regards,
> Carlo
> 
> 
> 
> Dott. Carlo Lazzaro
> Studio di Economia Sanitaria
> Via Stefanardo da Vimercate, 19
> 20128 Milano
> Tel/fax: 02/26000516
> Portatile: 335/6786741
> e-mail: carlo.lazzaro@tiscalinet.it
>                carlo.lazzaro@tin.it
> 
> -----Messaggio originale-----
> Da: owner-statalist@hsphsun2.harvard.edu
> [mailto:owner-statalist@hsphsun2.harvard.edu] Per conto di
> A.J.M.de_Craen@lumc.nl
> Inviato: lunedì 8 ottobre 2012 10:00
> A: statalist@hsphsun2.harvard.edu
> Oggetto: RE: st: Is there a similar command as roccomp for comparing two
> kaplan-meier curves?
> 
> Thank you Steve, I was indeed not completely clear. Let me retry.
> For 600 individuals I have calculated two measures of kidney function based
> on different blood parameters. First, I select those with a poor kidney
> function based on one variable, and run a survival analysis. Then I select
> those with a poor kidney function on the other variable, and run a survival
> analysis again. Obviously, there are many individuals in both analyses, but
> some only have a poor kidney function on one variable, and others only on
> the other. When I look at the two Kaplan-Meier curves in one graph, I see a
> clear difference between the two lines. How do I test whether they are
> statistically significant from each other?
> Regards,
> Ton
> 
> 
> 
> -----Original Message-----
> From: owner-statalist@hsphsun2.harvard.edu
> [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Steve Samuels
> Sent: maandag 8 oktober 2012 4:02
> To: statalist@hsphsun2.harvard.edu
> Subject: Re: st: Is there a similar command as roccomp for comparing two
> kaplan-meier curves?
> 
> 
> 
> Your question is not clear. There cannot be two KM curves that both are
> based on the same individuals, as the KM curve is unique, given the sample.
> As asked in the FAQ Section 3.3, please show us the Stata commands that
> produce the KM curves that you wish to compare. If you can, illustrate the
> problem in one the data sets referenced in the
> -help- for the command.
> 
> 
> Steve
> 
> 
> On Oct 7, 2012, at 3:32 PM, <A.J.M.de_Craen@lumc.nl>
> <A.J.M.de_Craen@lumc.nl> wrote:
> 
> Is there a similar command as roccomp for comparing two kaplan-meier curves?
> I want to compare the predictive value of two different variables in the
> same dataset. Note that the all individuals are in both K-M curves.
> Thanks,
> Ton de Craen
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/faqs/resources/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/faqs/resources/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/faqs/resources/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/faqs/resources/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/faqs/resources/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/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/