[R] Question on weighted Kaplan-Meier analysis of case-cohort design

[xiao-jun ma]

I have a study best described as a retrospective case-cohort design:  
the cases were all the events in a given time span surveyed, and the  
controls (event-free during the follow-up period) were selected in  
2:1 ratio (2 controls per case).  The sampling frequency for the  
controls was about 0.27, so I used a weight vector consisting of 1  
for cases and 1/0.27 for controls for coxph to adjust for sampling  
bias. Using the same weights in Kaplan-Meier analysis (survfit) gave  
very inaccurate survival curves (much lower event rate than expected  
from population). Are weighting handled differently between coxph and  
survfit? How should I conduct a weighted Kaplan-Meier analysis (given  
that survfit doesn't accept a weighted cox model) for such a design?

Any explanations or suggestions are highly appreciated,

xiaojun