R help - Sep 2004 - Bootstrapping with weighted data sample

Hi all!

Consider a sample, x, like this:
#
x<- matrix(rbind(4,8,0,2, 25,30,5,32), ncol=2)
#

Weight  Income
4    25
8    30
0    5
2    32

Here the "Weight" assigns the weight of each observation. It is easy
to
compute any measure of inequality, for instance

library(ineq)
Gini(rep(x[,2], x[,1]))

However, what happens is that the original sample is extended (from four 
observations to 14 (sum(x[,1]) instead of length(x[,1])). The problem I 
have arises when I try to compute a confidence interval surrounding this 
Gini coefficient via bootstrap, because the bootstrap-sample should of 
course not exceed the number of observations.

Has anybody an idea or experience with such a problem.

Thanks in advance.


P.S. I am using library(bootstrap) with bcanon() to obtain boostrap 
confidence intervals.

s.

Salvatore Barbaro writes, in part:

> Consider a sample, x, like this:
> #
> x<- matrix(rbind(4,8,0,2, 25,30,5,32), ncol=2)
> #
>
> Weight  Income
> 4    25
> 8    30
> 0    5
> 2    32
>
> Here the "Weight" assigns the weight of each observation.
> P.S. I am using library(bootstrap) with bcanon() to obtain boostrap
> confidence intervals.
You may want to use functions from the boot package instead. The boot
function accommodates weighted observations in drawing new samples.


**********************************************************
Cliff Lunneborg, Professor Emeritus, Statistics &
Psychology, University of Washington, Seattle
cliff at ms.washington.edu