How to run Bayesian Relative Survival Analysis for SAS?

[vincent]

Hi all,

May i know how do I run bayesian relative survival analysis in SAS?  From what i know, a website by Paul Dickman contains SAS code for estimating and modeling relative survival, but no bayesian relative surival. The paper, Spatial variation in prostate cancer survival in the Northern and Yorkshire region of England using ... uses Bayesian relative survival. I am currently learning relative survival analysis from the website, http://www.pauldickman.com/rsmodel/sas_colon/. I have look through Bayesian Survival Analysis(2001) by Joseph George Ibrahim, Ming-Hui Chen, Debajyoti Sinha and would like to try out bayesian relative survival analysis in SAS.

From SAS/STAT® 9.2 User’s Guide, i know that  LIFEREG and PHREG procedures contains procedures for bayesian survival analysis.

But i was wondering is there any additional steps or differences between bayesian relative survival and bayesian survival? May i know whether can byesian relative survival analysis be run for the dataset below (colon.sas7bdat) and what are the steps or any macros that i need to download? (For your information, relative survival is the method of choice for estimating patient survival using data collected by population-based cancer registries although its utility is not restricted to studying cancer( Dickman and Adami 2006; Dickman et al. 2004).”, which is a concept defined by Berkson (1942) and Berkson & Gage (1950).Two data files are required in order to estimate relative survival; a file containing individual-level data on the patients (colon.sas7bdat) and a file containing expected probabilities of survival(popmort.sas7bdat) for a comparable general population.)

Thanks a lot.

Vincent

[Rick_SAS]

I would be careful of using some of the older papers. Although the code/macros should still work, SAS has added a lot of Bayesian features in the last few releases. These will likely make the analysis simpler to program.

An overview of survival analysis procs is at http://support.sas.com/documentation/cdl/en/statug/63962/HTML/default/viewer.htm#introsurv_toc.htm

The link includes a section titled "Bayesian Survival Analysis with SAS/STAT Procedures."

[vincent]

Hi, Rick, thanks a lot for your reply

I have read through the 2 procedure, LIFEREG and PHREG procedures, which contains procedures for bayesian survival analysis. But i was wondering do these procedure can also applied to Bayesian Relative Survival Analysis? Or I need to find macros or type other codes to account for the Bayesian Relative Survival Analysis? I think there might difference when Bayesian Relative Survival Analysis come into play. "Relative survival analysis is used to model the excess risk of a certain subpopulation relative to the natural mortality risk, i.e. the base risk that is present in the whole population. Such models are typically used in the area of clinical studies, that aim at identifying prognostic factors for disease specific mortality with data on specific causes of death being not available." [Hennerfeind, Andrea and Held, Leonhard (2006): A Bayesian geoadditive relative survival analysis o...

http://epub.ub.uni-muenchen.de/1881/1/paper_515.pdf

Thanks once again.

[Reeza]

I believe that's one type of analysis we run in R here, they have a good package for it compared to what's currently available in SAS.

[vincent]

Dear Reeze, thanks for your reply.

From http://cran.r-project.org/web/packages/available_packages_by_name.html, i know that the package relsurv http://cran.r-project.org/web/packages/relsurv/index.html is for Relative survival and the package splinesurvhttp://cran.r-project.org/web/packages/splinesurv/index.html is for Nonparametric bayesian survival analysis. But now i am looking for "Bayesian Relative Survival Analysis" packages or macros. Do you know of any R packages or SAS macros that run this statistical test. So far, i have been searching but has not found any R packages or SAS macros that run "Bayesian Relative Survival Analysis". Thanks a lot.