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

RE: st: At risk table [for Kaplan Meier plots]


From   Matthew Sydes <Matthew.Sydes@ctu.mrc.ac.uk>
To   "'statalist@hsphsun2.harvard.edu'" <statalist@hsphsun2.harvard.edu>
Subject   RE: st: At risk table [for Kaplan Meier plots]
Date   Mon, 6 Jun 2005 15:11:19 +0100

Can I please echo Horea's concern about this limitation in Stata and have
this added this to the Stata wishlist? I had rather hoped that this
particular issue would have been resolved for Stata 9.

I agree that -stsatrisk- is a useful package which I use often, but it is
limited in its presentation and its graphs do need manual manipulation
before they can be used more formally.  Working in clinical trials in
cancer, Kaplan-Meier plots are our bread and butter.

Yours hopefully,

Matt

================================
Matthew Sydes
Senior Medical Statistician

T: 020 7670 4798 (direct)
T: 020 7670 4700 (switchboard)
F: 020 7670 4814/5
E: matthew.sydes@ctu.mrc.ac.uk
W: www.ctu.mrc.ac.uk

Cancer Group
MRC Clinical Trials Unit
222 Euston Rd
London 
NW1 2DA
UK
================================


-----Original Message-----
From: Nick Cox [mailto:n.j.cox@durham.ac.uk]
Sent: 06 June 2005 14:36
To: statalist@hsphsun2.harvard.edu
Subject: RE: st: At risk table


OK; sorry I missed that. 

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

> -----Original Message-----
> From: owner-statalist@hsphsun2.harvard.edu
> [mailto:owner-statalist@hsphsun2.harvard.edu]On Behalf Of Horea Feier
> Sent: 06 June 2005 13:49
> To: statalist@hsphsun2.harvard.edu
> Subject: Re: st: At risk table
> 
> 
> Yes, I am aware of -stsatrisk- (please see my first email).
> 
> However, it places by default the values of the subjects at risk
> inside the graphregion.
> 
> I was looking for a way to place them instead underneath the graph,
> in a table, as some journals (eg New England Journal of Medicine)
> require.
> 
> 
> On Jun 6, 2005, at 3:09 PM, Nick Cox wrote:
> 
> > On the contrary, Svend referred to -stsatrisk-. See his
> > email again.
> >
> > Nick
> > n.j.cox@durham.ac.uk
> >
> > Horea Feier
> >
> >
> >> Thank you for your example script...It shows that you can 
> insert the
> >> table, more or less "by hand", but it works.
> >>
> >> In fact I was looking for some program which could create 
> this table
> >> automatically, so to say, and be able to place it in a specified
> >> position.
> >>
> >>    I understand that you are not aware of such a 
> contributed program?
> >>
> >>    Thanks for your great example anyway, Horea
> >>
> >>
> >> On Jun 5, 2005, at 4:17 PM, Svend Juul wrote:
> >>
> >>
> >>> Horea asked how to display a number at risk table below a Kaplan-
> >>> Meier graph.
> >>>
> >>> The is the intent of -stsatrisk-, but the author correctly warns
> >>> that it does not always work well.
> >>>
> >>> It can be done, however, but not easily. Start with running -
> >>> stsatrisk- to get the numbers right. Below I show an example of
> >>> constructing the table. It works, but it required quite a bit of
> >>> trial and error. I used -scheme lean1- putting the legend to the
> >>> right of the plot area, to avoid conflict between legend 
> and table.
> >>>
> >>> Hope this helps
> >>> Svend
> >>> ----------------------------------------------------
> >>> set scheme lean1
> >>> sts graph                                         ///
> >>>   ,                                               ///
> >>>   by(screengr) per(1000)                          ///
> >>>   fail                                            ///
> >>>   clpattern(- l)                                  ///
> >>>   title("")                                       ///
> >>>   graphregion(margin(b+6))                        ///
> >>>   plotregion(margin(l=0 b=0))                     ///
> >>>   xtitle(Months of follow-up)                     ///
> >>>   ytitle("Cumulated AAA mortality per 1000")      ///
> >>>   xscale(range(0 60))                             ///
> >>>   xlabel(0(12)60)                                 ///
> >>>   ylabel(0(1)5 , format(%1.0f) nogrid)            ///
> >>>   legend(label(1 "Controls") label(2 "Invited"))  ///
> >>>   text(-0.93 -5 "Invited" , size(*0.8) place(w))  ///
> >>>   text(-1.2 -5 "Controls" , size(*0.8) place(w))  ///
> >>>   text(-0.93 0 "6333" , size(*0.8))               ///
> >>>   text(-1.2 0 "6306" , size(*0.8))                ///
> >>>   text(-0.93 12 "6172" , size(*0.8))              ///
> >>>   text(-1.2 12 "6120" , size(*0.8))               ///
> >>>   text(-0.93 24 "5499" , size(*0.8))              ///
> >>>   text(-1.2 24 "5452" , size(*0.8))               ///
> >>>   text(-0.93 36 "4971" , size(*0.8))              ///
> >>>   text(-1.2 36 "4905" , size(*0.8))               ///
> >>>   text(-0.93 48 "4305" , size(*0.8))              ///
> >>>   text(-1.2 48 "4286" , size(*0.8))               ///
> >>>   text(-0.93 60 "3644" , size(*0.8))              ///
> >>>   text(-1.2 60 "3657" , size(*0.8))
> >>> -----------------------------------------------------
> >>>
> >
> > *
> > *   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/
> >
> >
> 
> *
> *   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/
> 

*
*   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/
*
*   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