[R] Bootstrapping help

From: Ben Ridenhour <securebenji-general_at_yahoo.com>
Date: Wed 18 Jan 2006 - 17:02:49 EST

 I am new to using R and I am having problems get boot() to work properly. Here is what I am trying to do:  

 I have statistic called "cs". cs takes a data matrix (154 x 5) and calculates 12 different scores for me. cs outputs the data as a vector (12 x 1). cs doesn't really use weights, per se, however I have included this as one of the 2 arguments cs can take.  

 I try performing a bootstrap by issuing:  myout<-boot(data, cs,R=999)
 I have tried other versions where I specify stype="w", etc...  

 The problem I get is that the dataset does not seem to be resampled. I end up with 999 replicates that have the exact same value of the output of cs.  

 In the end I have something like  

 Bootstrap Statistics :

          original        bias    std. error
 t1*   0.865122275  1.698641e-14           0
 t2*  -0.005248414 -9.627715e-17           0
 t3*  -0.052833740 -8.812395e-16           0
 t4*   0.807040121  1.287859e-14           0
 t5*   0.542082588 -9.103829e-15           0
 t6*  -0.018617838 -7.285839e-17           0
 t7*   0.006409704  1.422473e-16           0
 t8*   0.529874453  8.104628e-15           0
 t9*   0.074804390  2.359224e-16           0
 t10* -0.007153634  1.301043e-16           0
 t11* -0.018241243 -2.359224e-16           0
 t12*  0.049409513 -1.200429e-15           0

 Clearly the bootstrap is not working. What am I doing wrong?  


Benjamin Ridenhour
School of Biological Sciences
Washigton State University
P.O. Box 644236
Pullman, WA 99164-4236
Phone (509)335-7218

"Nothing in biology makes sense except in the light of evolution." -T. Dobzhansky

        [[alternative HTML version deleted]]

R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html Received on Wed Jan 18 17:10:17 2006

This archive was generated by hypermail 2.1.8 : Fri 03 Mar 2006 - 03:42:05 EST