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

st: Re: Patterns in an area graph


From   "Dominic Muston" <Dominic.Muston@icr.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: Re: Patterns in an area graph
Date   Wed, 08 Jun 2005 09:33:13 +0100

Thank you, Nicks C and W. I'm only a novice medical statistician myself
- I find lists like statalist very helpful.

I think we might stick to an untransformed scale, because the idea of
competing risks and their effects on long-term survival is perhaps
already a bit mind-blowing for the intended audience of
non-statisticians! Log survival might produce straight(er) lines I
suppose, but what we're drawing attention to is how small one of the
competing risks is in certain patient subgroups, rather than the shape
of the curve.

The area in the survival plot doesn't really mean much and readers
should probably be considering the vertical distance between 100% and
the survival probability lines, rather than an area. Further reason to
go for a line graph instead I suppose, though it means that our graph
will look a bit different to others' previous work.

I didn't know of the text() option, so I'll play around with that too.

Thanks again,

Dominic Muston.
*
*   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