[R] Bootstrap

[Daniel Malter]

Two data frames, data.x and data.y with one random variable and one
identifier variable each. Two methods to merge them, one the "brute force"
approach, the other using R's merge() function:

data.x=data.frame(rnorm(100,0,1),1:100)
##data.x is already orderer by id

names(data.x)=c("x","x.id")

data.y=data.frame(rnorm(100,0,1),sample(1:100,replace=F))
##data.y is not ordered by id

names(data.y)=c("y","y.id")

##order y by id
data.y.new=data.y[order(data.y$y.id),]

##after ordering y, just bind the datasets together
merged.data1=data.frame(data.x,data.y.new)
merged.data1
##This works only if the identifier variable is unique

##more elegant solution to merge datasets by merge()
merged.data2=merge(data.x,data.y,by.x="x.id",by.y="y.id")
merged.data2
##This also works if identifier is not unique

Cheers,
Daniel


-------------------------
cuncta stricte discussurus
-------------------------

-----Ursprüngliche Nachricht-----
Von: r-help-bounces at r-project.org [mailto:r-help-bounces at r-project.org] Im
Auftrag von Marcioestat
Gesendet: Tuesday, October 21, 2008 5:24 PM
An: r-help at r-project.org
Betreff: [R] Bootstrap


Hi listers,
I've been work on a bootstrap estimator and I don't know how to make a
certain manipulation at the data.
As an example I have the following data and samples... I need now to
identify the vector in wich I sampled the id, I mean that I have to merge
the files having the key as the id of the samples in order to find the
vector that were selected.
Thanks in advance,
Márcio

id<-seq(1:49)
x<-runif(49)
u<-runif(49)
data<-cbind(id,x,u)
B<-10
sampling<-lapply(1:B, function(i) sample(id, replace=T))

--
View this message in context:
http://www.nabble.com/Bootstrap-tp20099684p20099684.html
Sent from the R help mailing list archive at Nabble.com.

______________________________________________
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.