1The purpose of this (XS) module is to calculate the median (or in principle also
2other statistics) with confidence intervals on a sample. To do that, it uses a
3technique called bootstrapping. In a nutshell, it resamples the sample a lot of
4times and for each resample, it calculates the median. From the distribution of
5medians, it then calculates the confidence limits.
6
7In order to implement the confidence limit calculation, various other functions
8had to be implemented efficiently (both algorithmically efficient and done in
9C). These functions may be useful in their own right and are thus exposed to
10Perl. Most notably, this exposes a median (and general selection) algorithm that
11works in linear time as opposed to the trivial implementation that requires
12O(n*log(n)).
13