Not so much an R question, as a methodology one...
Dealing with some reviewers comments, one of the reviewers suggests
bootstrapping my group means and standard deviations since 2 of my 3 groups
have a small sample size. My data is geochemical data, and a variety of
clustering methods finds 3 groups in the data. One group has 50 members,
another group has 10 members and another group 12 members. LDA with
cross-validation gives a 92% correct classification rate.
Anyway, my question is this---
WHat is the best or proper way to present the results of a bootsrapped mean
and standard deviation? I ask this since looking through both Efron's and
Tibshirani's AN INTRODUCTION TO BOOTSTRAP, and Davison's and
Hinkley's book
they don't necessarily address a question this simple. I don't think
the
editor is going to one to see 48 histograms (8 variables for 3 groups, mean
and standard deviation).
Or should I quit looking at boot and bootstrap, and just do the sample with
replacement that is in R, and calculate the mean and standard deviation from
there?
Any advice would be appreciated (particularly since I lost the argument with
the editor...).
Best, Mark Hall
-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !) To: r-help-request at
stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._
