st: relative survival

[Enzo Coviello <enzo.coviello@alice.it>]

Hi all,

Let me add some more information on the relative survival in Stata:


   The method that -strel- and other similar programmes use for
   calculating crude or observed survival is the actuarial (life table)
   method. You don't necessarily need to read a specific Stata book as
   this is implemented in other stats packages and the methods behind
   it are well know. You should be able to get the same crude survival
   using -ltable- in Stata, with your code it would be this:

-strel-, as far as I know, should use a maximum likelihood approach for estimating the relative survival, i.e. (observed surv) / (expected surv).

-strs- implements a life table approach for estimating the same function. The observed survival computed by -strs- is identical to that computed by -ltable-.


What -strel- names as -crude survival- should be the observed surv computed as back transformation of the cumulative hazard. As far as I know -strel- does not compute the crude probability (cumulative incidence) of death whereas -strs- does compute this function by implementing the method described by Cronin and Feuer (Stat in Med 2000)


I would also note that in the last updated version -strs- adds the opportunity to estimate the Pohar-Perme net survival estimator, a true important innovation in the population survival analysis (Pohar-Perme Biometrics 2011).

Best wishes

Enzo



--
Enzo Coviello
Epidemiology Unit - Cancer Registry ASL BT
Piazza Umberto 1
76121 BARLETTA (BT)
Italy
mobile +39 347 5016016
tel +39 0883 577329
fax +39 0883 577288

*
*   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/