[R] Bootstrap

Shentu yue_shentu at merck.com
Mon Aug 9 15:02:45 CEST 2010

You should bootstrap the two groups separately. The bootstrap sample you get
do not follow the same order as the original sample, so the first 62
observations are coming from both groups.  What you bootstrapped is
essentially the difference between the pooled mean and itself, which would
no doubt come up as 0.
View this message in context: http://r.789695.n4.nabble.com/Bootstrap-tp2317776p2318480.html
Sent from the R help mailing list archive at Nabble.com.

More information about the R-help mailing list