Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.

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

From |
Maarten Buis <maartenlbuis@gmail.com> |

To |
statalist@hsphsun2.harvard.edu |

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

Date |
Mon, 11 Jul 2011 08:41:08 +0200 |

On Fri, Jul 8, 2011 at 8:13 PM, <petretta@unina.it> wrote: > I know that the baseline survival function of the Cox model without > covariates is the same as the Kaplan Meier survival function. > However, it is unclear for me why the survival function of a Cox model with > covariates obtained at the mean values of the covariates is different from > baseline survival function of the Cox model without covariates. Because the relationship between the covariates and the survivor function is a non-linear one. Remember that applying a non-linear transformation to a variable x and than compute the mean is not the same as computing the mean of variable x and than apply that non-linear transformation. If this is new to you, try the example below: *---------- begin example ---------- sysuse nlsw88, clear gen ln_w = ln(wage) sum ln_w sum wage di ln(r(mean)) *------------ end example ---------- Hope this helps, Maarten -------------------------- Maarten L. Buis Institut fuer Soziologie Universitaet Tuebingen Wilhelmstrasse 36 72074 Tuebingen Germany http://www.maartenbuis.nl -------------------------- * * 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/

**References**:**st: Survival function of regression Cox model postestimation***From:*petretta@unina.it

- Prev by Date:
**st: marginal effects and std. coefficients after xtlogit** - Next by Date:
**Re: st: Testing independence of factor variables in a non-linear specification** - Previous by thread:
**st: Survival function of regression Cox model postestimation** - Next by thread:
**st: Inserting non blank observations multiple times** - Index(es):