R-beta: Result_abcnon
Guido Masarotto
guido at sirio.stat.unipd.it
Fri Jul 24 10:52:21 CEST 1998
On Fri, Jul 24, 1998 at 08:55:36AM +0700, Nikom Thanomsieng wrote:
> Dear, Sir.
> I run R program (rw0613b) under Windows 95 and used Functions for the
> Book
> "An Introduction to the Bootstrap", that help in html files to compute
> nonparametric
> abc confidence intervals for the mean. I write command following
> "
> > library(bootstra)
> > library(help = bootstra)
> Read 8 items
> abcnon Nonparametric ABC Confidence Limits
> abcpar Parametric ABC Confidence Limits
> bcanon Nonparametric BCa Confidence Limits
> bootpred Bootstrap Estimates of Prediction Error
> bootstrap Non-parametric Bootstrapping
> boott Bootstrap-t Confidence Limits
> crossval K-fold Cross-Validation
> jackknife Jackknife Estimation
> > x <- rnorm(10)
> > x
> [1] 0.1808591 0.4303385 1.4218043 0.7222164 -0.9713840 0.6121021
> [7] 0.0555533 -0.9721635 0.5111223 -2.0564528
> > theta <- function(p,x) {sum(p*x)/sum(p)}
> > results <- abcnon(x, theta)
> >
> "
> The command that I wrote can not show the output of abc
> intervals for
> the mean.
Would you mind to be more precise?
I have just checked your example on a machine with rw0613b installed
and the results seems correct: abcnon returns a list that you can see
in the standard way:
> results <RETURN>
There are only one thing that I cannot understand in your example.
rw0613b is the binary version for Win95/WinNT which support
long file names. Hence, the name of the package should be
"bootstrap" not "bootstra". "bootstra" is the truncated name
in the Win3.1/Win32s version (rwin31b). I have not checked
the archives in CRAN but the original one at
ftp://sirio.stat.unipd.it/pub/R
seems correct.
Anyway, this should not change the results. rwin31b is different
from rw0613b only for the name mangling (long file names -> 8.3 names).
Indeed, I could run your example with rwin31b, too.
guido m.
-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
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
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._
More information about the R-help
mailing list