Approaches to compare performance of the nested competing risk models

[haoduonge]

Hi all,

Please share approaches to compare performance of the two models below.

Thank you!

Hao

*MODEL 1: 1 VARIABLE;

proc phreg data = ALL;

CLASS X1_3CAT(ref='0');

model FU_TIME_YRS *OUTCOME(0)= X1_3CAT/RL eventcode=1;

run;

*MODEL 2: 2 VARIABLES;

proc phreg data = ALL;

CLASS X1_3CAT(ref='0') X2_2CAT(ref='0');

model FU_TIME_YRS *OUTCOME(0)= X1_3CAT X2_2CAT/RL eventcode=1;

run;

[SteveDenham]

What sort of measure do you want to use for performance? Machine performance can be obtained from the log, in terms of cpu time and elapsed time. Model performance for PHREG is harder as there isn't a real good equivalent to the RMSE (smaller is better in terms of model performance). I suppose you could look at the relative sizes of the standard errors for various parameters, but that overlooks the danger of overfitting. With only two independent variables that may not be an issue, however.

SteveDenham