boot & boot.ci

classic Classic list List threaded Threaded
1 message Options
Reply | Threaded
Open this post in threaded view
|

boot & boot.ci

Kuba-4
Dear all,
   I've a problem with bootstarp package... I want to bootstrap
correlation ratio of some data.
 my code is:
 f<-function(d) cov(d$x,d$y)/sqrt(var(x)*var(y))
 boot(d,f,R)
 
 As a result I got an error:
 Error in statistic(data, original, ...) : unused argument(s) (..
 .)
 
 d is a data.frame containing two vectors with labels x and y.
 
 Also, another thing I have problem with is generating the
confidence interval using boot.ci
 
 if I write:
 d.boot<-boot(d,cor,R)
 boot.ci(d.boot,conf=0.95,type="bca")
 
 I get an error:
 Error in bca.ci(boot.out, conf, index[1], L = L, t = t.o, t0 =
 t0.o, h = h,  :
         estimated adjustment 'a' is NA
 
 Last question is how to generate a studentized intervals for
 such data?
 
 Thanks,
 Kuba

Kuba

----------------------------------------------------
Cameron Diaz i Toni Collette w filmie SIOSTRY
W kinach od 27 stycznia 2005 r.
http://klik.wp.pl/?adr=http%3A%2F%2Fadv.reklama.wp.pl%2Fas%2Fsiostry.html&sid=641

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html