Re: st: RE: Violation of porportional hazard assumption in Cox duration model - consequences?

["Nils Braakmann" <nilsbraakmann@googlemail.com>]

Dear Peter,

thank you! The results look favorable.

Just out of curiosity (if you or anyone else could spare the time):
Would there have been any remedy if the results differed much between
the stratified and non-stratified results, e.g. introducing
interactions of the respective variable with (some function of)
analysis time?

Again thanks for the advice and best regards,
Nils

On Mon, Mar 17, 2008 at 11:25 AM, Peter Jepsen <PJ@dce.au.dk> wrote:
> Dear Nils,
>
>  One possibility is to stratify your Cox model according to the variables
>  with non-proportional hazards and see whether that changes the hazard
>  ratios for your variables of interest. If it doesn't, then the
>  non-proportionality is of no consequence for what you are interested in.
>
>  Best regards,
>  Peter.
>
>  -----Original Message-----
>  From: owner-statalist@hsphsun2.harvard.edu
>  [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Nils
>  Braakmann
>  Sent: 17. marts 2008 11:00
>  To: statalist@hsphsun2.harvard.edu
>  Subject: st: Violation of porportional hazard assumption in Cox duration
>  model - consequences?
>
>  Dear all,
>
>  I am currently estimating a Cox proportional hazard model on duration
>  data. Unfortunately, tests indicate that the proportional hazard
>  assumption is violated for some variables. As these  are mere control
>  variables which are not of central interest, I ask myself whether
>  there are any consequences of this violation for the other parameters
>  (for which the proportional hazard assumption holds).
>
>  Any help on this issue would be greatly appreciated.
>  Best regards,
>  Nils
>  *
>  *   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/
>
>  *
>  *   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/
>
*
*   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/