Hi all, Sorry if this has been answered already, but I couldn't find it in the archives or general internet. Is it possible to implement the gompertz distribution as survreg.distribution to use with survreg of the survival library? I haven't found anything and recent attempts from my side weren't succefull so far. I know that other packages like 'eha' and 'flexsurv' offer functions similar to survreg with gompertz support. However, due to the run-time environment were this needs to be running in the end, I can't use these packages :( Same questions for the gompertz-makeham distribution. Many thanks! Matthias
On Nov 15, 2012, at 5:38 AM, Matthias Ziehm wrote:> Hi all, > > Sorry if this has been answered already, but I couldn't find it in the archives or general internet.A Markmail/Rhelp search on: gompertz survreg ...brings this link to a reply by Terry Therneau. Seems to address everything you asked and a bit more http://markmail.org/search/?q=list%3Aorg.r-project.r-help+gompertz+survreg#query:list%3Aorg.r-project.r-help%20gompertz%20survreg+page:1+mid:6xdlsmo272oa7zkw+state:results (Depending on how your mailer breaks URLs you may need to paste it back together.)> > Is it possible to implement the gompertz distribution as survreg.distribution to use with survreg of the survival library? > I haven't found anything and recent attempts from my side weren't succefull so far. > > I know that other packages like 'eha' and 'flexsurv' offer functions similar to survreg with gompertz support. However, due to the run-time environment were this needs to be running in the end, I can't use these packages :( > > Same questions for the gompertz-makeham distribution. > > Many thanks! > > Matthias-- David Winsemius, MD Alameda, CA, USA
The short answer is "sort of". Medium is that survreg implements the model framework found in Kalbfeisch and Prentice, The statistical analysis of failure time data, chapter, chapter 2.2. The ime variable T has f(time) ~ X' beta + sigma * W where W is an error term from some distribution and f is a fixed function (usually identity or log). Any distribution that can be shoehorned into this framework can be fit with survreg. A longer and more detailed discussion is found in Division of Biostatistics Technical Report #53, Mayo Clinic, "A package for survival analysis in S". One day I need to update this and make it a vignette for the package.... http://mayoresearch.mayo.edu/mayo/research/biostat/techreports.cfm Terry Therneau -------- begin included message ------- Hi all, Sorry if this has been answered already, but I couldn't find it in the archives or general internet. Is it possible to implement the gompertz distribution as survreg.distribution to use with survreg of the survival library? I haven't found anything and recent attempts from my side weren't succefull so far. I know that other packages like 'eha' and 'flexsurv' offer functions similar to survreg with gompertz support. However, due to the run-time environment were this needs to be running in the end, I can't use these packages :( Same questions for the gompertz-makeham distribution. Many thanks! Matthias
Reasonably Related Threads
- Using coxph with Gompertz-distributed survival data.
- significant difference between Gompertz hazard parameters?
- Gompertz-Makeham hazard models---test for significant difference
- Parametric survival models with left truncated, right censored data
- fitting a gompertz model through the origin using nls