R help - Jun 2009 - Studentized intervals

I am trying to find studentized bootstrap intervals for the skewness of a data
set. I have tried the following (nerve.dat is a set of data containing
observations on one variable) (using Windows XP):

x <- scan("e:/Flashbackup2009/Nonparametrics/nerve.dat")
n <- length(x)
library(e1071)
skewness(x)
library(boot)
sampleskew <- function(x,d) {return(skewness(x[d]))}
bb <- boot(x,sampleskew,R=1000)
boot.ci(bb)


This gives four intervals (Normal, Basic, Percentile, BCa)
But gives the following warning message:

Warning message:
In boot.ci(bb, type = "all") :
  bootstrap variances needed for studentized intervals
The questions is: Why does the function not provide the bootstrap variances (or
estimates thereof) for computing the studentized intervals?
Another question: How then can I compute the studentized intervals without
physically doing a double bootstrap. Does the function use a "nonparametric
delta mathod"?

Any help is much appreciated. I have probably overlooked something?

Thank you.
Jacob


Jacob L van Wyk, Dept. of Statistics, University of Johannesburg (APK),
Box 524, Auckland Park, 2006.
Office: +27 11 559 3080, Fax: +27 11 559 2499


________________________________
This email and all contents are subject to the following disclaimer:

http://www.uj.ac.za/UJ_email_legal_disclaimer.htm

	[[alternative HTML version deleted]]

The help page ?boot.ci says

      Variance estimates are required for studentized intervals.
                             ^^^^^^^^

(and the warning you got repeated the point).

Package 'boot' is support software for a book by Davison & Hinkley 
which explains how to used boot.ci() for studentized examples and has 
several examples.  You will need to study it for further elucidation.


On Fri, 12 Jun 2009, Van Wyk, Jaap wrote:
> I am trying to find studentized bootstrap intervals for the skewness of a
data set. I have tried the following (nerve.dat is a set of data containing
observations on one variable) (using Windows XP):
>
> x <- scan("e:/Flashbackup2009/Nonparametrics/nerve.dat")
> n <- length(x)
> library(e1071)
> skewness(x)
> library(boot)
> sampleskew <- function(x,d) {return(skewness(x[d]))}
> bb <- boot(x,sampleskew,R=1000)
> boot.ci(bb)
>
>
> This gives four intervals (Normal, Basic, Percentile, BCa)
> But gives the following warning message:
>
> Warning message:
> In boot.ci(bb, type = "all") :
>  bootstrap variances needed for studentized intervals
> The questions is: Why does the function not provide the bootstrap 
> variances (or estimates thereof) for computing the studentized 
> intervals? Another question: How then can I compute the studentized 
> intervals without physically doing a double bootstrap. Does the 
> function use a "nonparametric delta mathod"?
>
> Any help is much appreciated. I have probably overlooked something?
>
> Thank you.
> Jacob
>
>
> Jacob L van Wyk, Dept. of Statistics, University of Johannesburg (APK),
> Box 524, Auckland Park, 2006.
> Office: +27 11 559 3080, Fax: +27 11 559 2499
>
>
> ________________________________
> This email and all contents are subject to the following disclaimer:
>
> http://www.uj.ac.za/UJ_email_legal_disclaimer.htm
>
> 	[[alternative HTML version deleted]]
>
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>
-- 
Brian D. Ripley,                  ripley at stats.ox.ac.uk
Professor of Applied Statistics,  http://www.stats.ox.ac.uk/~ripley/
University of Oxford,             Tel:  +44 1865 272861 (self)
1 South Parks Road,                     +44 1865 272866 (PA)
Oxford OX1 3TG, UK                Fax:  +44 1865 272595