This is the mail archive of the
gsl-discuss@sourceware.org
mailing list for the GSL project.
New module for running statistics calculations
- From: Patrick Alken <patrick dot alken at Colorado dot EDU>
- To: "gsl-discuss at sourceware dot org" <gsl-discuss at sourceware dot org>
- Date: Thu, 16 Apr 2015 16:44:29 -0600
- Subject: New module for running statistics calculations
- Authentication-results: sourceware.org; auth=none
Hi all,
I've just added a new module to GSL for running (or online)
statistics - ie: computing the mean, variance, standard deviation,
skewness, kurtosis, median, and arbitrary percentiles on the fly with a
single pass algorithm, without needing to store the whole dataset in
memory at once.
The mean, variance, standard deviation, skew and kurtosis are exact
computations. The median and p-quantile algorithm provides an
approximation to the actual quantile, using the algorithm of:
R. Jain and I. Chlamtac, The P^2 algorithm for dynamic
calculation of quantiles and
histograms without storing observations, Communications of the ACM,
Volume 28 (October), Number 10, 1985, p. 1076-1085.
It is now in the 'master' branch on the git and documented. I'll add an
example program a little later this week. Any feedback is welcome.
Patrick