st: RE: Checking goodness of fit of stcox when using the tvc() option

[graupel75@gmail.com]

Hello Nicole,

Easiest might be to do visual check with the predictions overlaid onto
the Kaplan-Meir Curves; crude, but should show any large-scale
deviations.

Also, check into Harrell’s c and Somer’s D statistics using -somersd-
(SSC); not sure about -tvc- here though.
Newson RB. Comparing the predictive power of survival models using
Harrell’s c or Somers’ D. The Stata Journal 2010; 10(3): 339–358.

The other option is to use -stpm2- (SSC) to fit Royston-Parmar
parametric survival models; a little time to get into, but allow for
much greater options in dealing with tvc effects.

cheers-
Andrew Lover

___________________________________________________________
Epidemiologist
Centre for Infectious Disease Epidemiology Research (CIDER)
Saw Swee Hock School of Public Health
National University of Singapore

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/