Dear users,
I'm trying to implement the nonparametric "two-stage" bootstrap
(Davison and
Hinkley 1997, pag 100-102) in R. As far as I understood, 'bootcov' is
the
most appropriate method to implement NONPARAMETRIC bootstrap in R when you
have clustered data (?). I read the 'bootcov' manual but I still have a
few
questions:
1 - When the variable 'cluster' is introduced, then only clusters will
be
resampled (with replacement)?
2 - I can implement 'two-stage' bootstrap in STATA by running bootstrap
sampling on top of the bootstrap command. Example: bootsrap cost,
cluster(group): bsampling cost treat
This means that in the 1st stage I resample clusters (with replacement) and
then resample individuals within those clusters.
I wonder whether we could do a similar procedure in R, i.e. if it is
sensible to do something like:
f<-boot(cost~treat)
mod<-bootcov(f, cluster, B=1000, coef.reps=TRUE)
Do you have any other ideas? Do I need to define 'fitter'?
Thanks a lot,
Manuel Gomes
--
View this message in context:
http://n4.nabble.com/Bootcov-for-two-stage-bootstrap-tp1819605p1819605.html
Sent from the R help mailing list archive at Nabble.com.
