Hi. I am a new R user trying to obtain bootstrap confidence intervals around vector correlations of Principal components.
My data is a data frame of eigenvector loadings from PC1 in the columns the rows are different species. I want to calculated the vector correlation and bootstrap confidence intervals for all species pairs. I have tried using simpleboot as pairs.boot seems to be an easy way of sampling from two vectors of data. The function I wrote "veccor" below works outside of the pairs.boot function. However in this function it seems to calculate all 1000 vector correlations as -1. ######## veccor function(x,y) ((sum((x)*(y)))/((sqrt(sum(y^2)))*(sqrt(sum(x^2))))) x<-as.vector(faVC[1,]) y<-as.vector(faVC[2,]) boot<-pairs.boot(x,y,veccor,1000) ######### I have also tried using the boot function but only end up sampling from on of my vectors of data. Any suggestions would be greatly appriciated! Thanks! Best, Becca ______________________________________________ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
