Notice: On March 31, it was **announced** that Statalist is moving from an email list to a **forum**. The old list will shut down on April 23, and its replacement, **statalist.org** is already up and running.

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

From |
"Airey, David C" <david.airey@vanderbilt.edu> |

To |
"statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu> |

Subject |
Re: Subject: Re: st: Survival function of regression Cox model postestimation |

Date |
Fri, 15 Jul 2011 17:39:32 -0500 |

. Following up one more time, I have to say that the Stata documentation is excellent. Read it and you eventually find insight and laugh as well. For example, I was concerned about continuous covariates without a 0, and I read in the stcox_postestimation PDF the following, where the last line was funny. "For these reasons, covariate values of 0 must be meaningful if you are going to specify the basechazard or basesurv option. As the baseline values move to absurdity, the first problem you will encounter is a baseline survivor function that is too hard to interpret, even though the baseline hazard contributions are estimated accurately. Further out, the procedure Stata uses to estimate the baseline hazard contributions will break down—it will produce results that are exactly 1. Hazard contributions that are exactly 1 produce survivor functions that are uniformly 0, and they will remain 0 even after adjusting for covariates. This, in fact, occurs with the Stanford heart transplant data: -output removed- The hint that there are problems is that the values of ch are huge and the values of s are close to 0. In this dataset, age (which ranges from 8 to 64 with a mean value of 45) and year (which ranges from 67 to 74) are the problems. The baseline functions correspond to a newborn at the turn of the century on the waiting list for a heart transplant!" -Dave > I've not much experience with survival models other than log-rank tests, but am reading more about them now. > > What's the interpretation of a continuous covariate if it doesn't include 0? A transformation can be done on an X covariate, e.g., X-#, to get the relative risk to when X=#. But if you don't do this transformation, and your data range doesn't naturally include 0, what happens to the interpretation? What do you do with a continuous covariate that varies from (-) to (+) values and you don't want the given 0 to be used? > > -Dave > > --- On Tue, Jul 12, 2011 at 6:40 PM, Mario Petretta wrote me privately: >> Anyway, there is a rule for applying a non-linear transformation to a >> continuous covariate in order to obtain a survival function of a Cox model >> with that covariate obtained at its mean value not different from >> baseline survival function of the Cox model without covariates? > > It is better to respond to the Statalist and not privately because if > you find my answer unclear, chances are that other people following > this thread may also find it unclear. > > No, Cox regression has a baseline hazard function not a baseline > survival function, and the baseline hazard function is the hazards at > different points in time when all explanatory/independent/x-variables > are 0 not fixed at the mean. > > Hope this helps, > Maarten * * 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/

- Prev by Date:
**Re: st: RD Optimal Bandwidth Algorithm sensitive to scaling?** - Next by Date:
**st: Backward Selection (AIC) with xtmixed** - Previous by thread:
**Re: Subject: Re: st: Survival function of regression Cox model postestimation** - Next by thread:
**st: zinb & testnl - testing nonlinear results** - Index(es):