The package bootBCa exports a single function, BCa, which finds confidence intervals using Efron's nonparametric bias-corrected and accelerated (BCa) bootstrap method. It is an enhanced derivative of the function bcanon, forked from bootstrap_2012.04-1. Adaptive determination of the number of bootstrap replications is supported and the amount of memory required is less by a factor of nboot.
Although the BCa function does not parallelize internally, multiple invocations of the function can profitably be run in parallel on different data (e.g., different treatments of an experiment). One script that does this is GECS (Gem for Experimental Computer Science).
For details please see the package documentation, which is linked here in HTML and PDF formats and included in the package in Rd format.
The package can be downloaded from here or installed
directly with the R command
Back to R-Forge project summary page for bootBCa