Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: parameterising strs to avoid cumulative relative survival increase


From   Enzo Coviello <enzo.coviello@alice.it>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: parameterising strs to avoid cumulative relative survival increase
Date   Wed, 26 Mar 2008 16:22:43 +0100

Dear all,
I am using strs to estimate relative survival and unless I make a mistake, I
notice that excess mortality rate are allowed to be negative and therefore
cumulative relative survival (ederer I, II or Hakulinen) is allowed to
increase.
Although I find interesting to have an estimation of a negative excess
mortality rate, I would prefer cumulative relative survival to stay constant
rather than increase when the number of deaths is smaller than expected
during the interval (like in strel). Is there a way to parameterise strs
this way?
Thank you for your help
Valerie


Yes, there is.

In -strs- the undocumented option -adjust- allowed to avoid the increase of the realtive survival.
Paul Dickman, the main author of the macro, is contrary to the use of this option for several reasons and so the -adjust- option has been removed.

In principle I agree with Paul Dickman even if I believe a macro is fundamentally a tool and the user has the responsibility to clearly document how they have been obtained.

I would suggest to write directly to Paul Dickman hoping that he replies (p < 1/1000000) and he reconsiders the opportunity to introduce again -adjust-

Best wishes.

Enzo

Enzo Coviello
UnitÓ di Epidemiologia e Statistica ASL BARI
Piazza V. Emanuele 14
70054 Giovinazzo (Bari)
Italy
tel./fax +39 080 3357867
mobile +39 347 5016 016
home +39 0883 695055


*
* 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