Dear Statalister,
I need to estimate the number needed to treat (NNT) for a treatment
variable after a multivariable stcox model.
Based on the recommendation of Douglas Altman (Calculating the number
needed to treat for trials where the outcome is time to an event - BMJ
1999),
I need to estimate the risk difference from the baseline survivor
function (and SE) at each level of the treatment variable at specific
time points (in my case 1, 2, and 3 years).
With the stcox postestimation command: "predict s0, basesurv"
I can estimate the baseline survivor function; but how can I get the
SE for the baseline survivor function at each time point?
I would appreciate any help on this issue,
Eduardo
PD: Stata 11 (Single-user 2-core)
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/