R in a Nutshell

Bootstrap Resampling

When analyzing statistics, analysts often wonder if the statistics are sensitive to a few outlying values. Would we get a similar result if we were to omit a few points? What are the range of values for the statistic? It is possible to answer this question for an arbitrary statistic using a technique called bootstrapping.

Formally, bootstrap resampling is a technique for estimating the bias of an estimator. An estimator is a statistic calculated from a data sample that provides an estimate of a true underlying value, often a mean, standard deviation, or a hidden parameter.

Bootstrapping works by repeatedly selecting random observations from a data sample (with replacement) and recalculating the statistic. In R, you can use bootstrap resampling through the boot function in the boot package:

library(boot)
boot(data, statistic, R, sim="ordinary", stype="i", 
     strata=rep(1,n), L=NULL, m=0, weights=NULL, 
     ran.gen=function(d, p) d, mle=NULL, simple=FALSE, ...)

Arguments to boot include the following.

Argument	Description	Default
data	A vector, matrix, or data frame containing the input data.
statistic	A function that, when applied to the data, returns a vector containing the statistic of interest. The function takes two arguments: the source data and a vector that specifies which values to select for each bootstrap replicate. The meaning of the second argument is defined by stype.
R	A numeric value specifying the number of bootstrap replicates.
sim	A character value specifying the ...