[R-pkgs] energy 1.0.1
Gabor Szekely
gabors at bgnet.bgsu.edu
Wed Mar 31 18:21:10 CEST 2004
R Users,
We would like to announce that Version 1.0.1 of the energy package is
now available on CRAN.
The energy package introduces a new class of statistical tests based
on the concept of Newton's potential energy. Included in the package are
* mvnorm.etest (test) and mvnorm.e (statistic)
A rotation invariant multivariate goodness-of-fit test,
implemented for testing multivariate normality with
estimated parameters
* eqdist.etest (test) and ksample.e (statistic)
A k-sample multivariate nonparametric test of equal distributions
(arbitrary number of samples and arbitrary dimension)
with optional incomplete statistics to support testing
arbitrarily large samples
* energy.hclust and edist
Hierarchical clustering based on e-distances and
cluster distance function
* poisson.mtest (test) and poisson.m (statistic)
Mean distance test of Poisson distribution, estimated mean
Here is a brief summary of the potential energy background of the
tests in the energy package:
Newton's gravitational force is inversely proportional to squared
Euclidean distances between pairs of objects, and the potential
energy is inversely proportional to their Euclidean distances. The
simplest choice for the absolute value of the force is constant, and
then the potential energy is proportional to the Euclidean distances
between pairs of objects. In statistics, the objects are the observed
random vectors, and thus our energy terms are Euclidean distances
between the pairs of sample elements: ||x_i - x_j||. Tests are based
on the Theorem that a suitable linear combination of these distances
(the potential energy of the 'statistical situation') is always
nonnegative, and equals 0 if and only if the null hypothesis holds.
Comments and suggestions are welcome. The description file is below.
Gabor Szekely and Maria Rizzo
----------------------------------------------------------------------
Description:
Package: energy
Title: E-statistics (energy statistics) tests of fit, clustering
Version: 1.0.1
Date: March 24, 2004
Author: Maria L. Rizzo <rizzo at math.ohiou.edu> and Gabor J. Szekely
<gabors at bgnet.bgsu.edu>
Description: E-statistics (energy) tests for comparing distributions:
multivariate normality, Poisson test, multivariate k-sample
test for equal distributions, hierarchical clustering by
e-distances. Energy-statistics concept based on a
generalization of Newton's potential energy is due to Gabor J.
Szekely.
Maintainer: Maria Rizzo <rizzo at math.ohiou.edu>
License: GPL 2.0 or later
--
****************************************
Gabor J. Szekely
Professor
Department of Mathematics and Statistics
Math Science Building
Bowling Green State University
Bowling Green, OH 43403-0221
E-mail: gabors at bgnet.bgsu.edu
Tel: 419-372-7474
Fax: 419-372-6092
http://www-math.bgsu.edu/~gabors/
More information about the R-packages
mailing list