The bstrap command allows for clusters.
bstrap progname [, reps(#) size(#) dots args(...) level(#) cluster(varnames)
idcluster(newvarname) saving(filename) double every(#)
replace noisily ]
..........
cluster(varnames) specifies the variable(s) identifying resampling
clusters. If specified, the
sample drawn during each replication is a bootstrap sample of
clusters.
However, you may want to take a look at glm, it allows for clustering and a
bootstrapped estimate of the variance.
Scott
----- Original Message -----
From: "Martin Raymond West" <[email protected]>
To: <[email protected]>
Sent: Wednesday, November 20, 2002 6:52 PM
Subject: Re: st: RE: Bootstrapping clustered residuals
> Thanks for your response, Nick. Unfortunately the standard -bs- command
> draws observations from the original data to construct bootstrap samples,
> not from the residuals of the model that is being estimated. I need to do
> the latter. Does anyone know of code that allows one to do this?
>
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
