[R] Confidence interval for difference in Harrell's c statistics (or equivalently Somers' D statistics)

2011-05-05 Thread Laura Bonnett
Dear All, I am trying to calculate a 95% confidence interval for the difference in two c statistics (or equivalently D statistics). In Stata I gather that this can be done using the lincom command. Is there anything similar in R? As you can see below I have two datasets (that are actually two

Re: [R] Confidence interval for difference in Harrell's c statistics (or equivalently Somers' D statistics)

2011-05-05 Thread David Winsemius
On May 5, 2011, at 8:20 AM, Laura Bonnett wrote: Dear All, I am trying to calculate a 95% confidence interval for the difference in two c statistics (or equivalently D statistics). In Stata I gather that this can be done using the lincom command. Is there anything similar in R? Have

Re: [R] Confidence interval for difference in Harrell's c statistics (or equivalently Somers' D statistics)

2011-05-05 Thread Laura Bonnett
Dear David, Thank you for your reply. I have come across rcorrp.cens before. However, I'm not sure it does quite what I want it to. It seems to compare whether one predictor is more concordant than another within the same survival function. I want to see whether one predictor is more