[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
Re: st: bootstrapping -- why am I not getting the full sample size?
Smith, Paul Bradley <SmithP5@uthscsa.edu> is having trouble with -bootstrap-:
> I'm trying to bootstrap a cost-effectiveness ratio, using a user-written
> program. Components are differences in cost of treatment, and
> differences in survival time. My user-written program works just right,
> but it bombs when submitted to the bootstrap routine. What happens is
> that the first resample (after the run on the entire dataset) contains a
> resample with about a third of the patients that were in the original
> sample. The truncated sample size exactly corresponds to the number of
> control group patients in the study.
Paul's user written command -myRatio- is using -stci-. Although -stci- is an
-rclass- command, it is using -regress- to perform some of its calculations.
-bootstrap- noticed that -e(sample)- was created by -myRatio-. By default,
-bootstrap- drops observations that appear to be outside the estimation
sample. Unfortunately, this is not desirable for use with -myRatio- being
that it is not an estimation command.
Paul can specify the -nodrop- option to keep -bootstrap- from dropping
observations in the dataset it is resampling from.
* For searches and help try: