Re: st: Smooth within Cox regression

[Richard Goldstein <richgold@ix.netcom.com>]

what do you mean by "a general smooth function" -- you might want to try 
searching "spline" (though Dupont's program is not included in the results for 
some reason) and you might want to look at -fracpoly- and at -mfp- in the 
reference manual

Rich

Tim Church wrote:

> I want to do a Cox regression with a continuous covariate, call it EF,
> and I want a general smooth function rather than a simple linear form
> for EF vs. the proportionality constant. Is there a way to specify such
> a form for a covariate in =93stcox=94? Or is there some other way to get a
> smooth for a continuous covariate in Cox regression? The =93Introduction
> to Survival Analysis in Stata=94 book doesn=92t cover this.
>
> --=20
>    __________________________________ ___________________________________
> |                                  |                                   |
> | Timothy R. Church, Ph.D.         |420 Delaware St SE, MMC 807, Rm1260|
> | Professor                        |Minneapolis, Minnesota  55455      |
> | Div of Environ Health Sciences   |Office:612-626-1494,612-625-9091   |
> | Univ of Minn Schl of Pub Health  |Fax:   612-626-4837,612-624-3370   |
> |                                  |                                   |
> | http://enhs.umn.edu/files/facultypages/church.html                   |
> |__________________________________|___________________________________|
*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/