zt: a software tool for simple and partial Mantel tests
|
| |
| Principle |
Mantel's test
(1967, 1970) is a widely used method for assessing the
relationships between two distance matrices or, more
generally, two resemblance or proximity matrices. It is
classically used to compare genetic and geographical
distances in populations genetic studies. But it can also
be used in the fields of ecology, sociology,
anthropology, psychometry, etc. There are a growing
number of publications refeering to this test in the
literature.
This test involves measuring the association between the
elements in two matrices by a suitable statistic, and
then assessing the significance of this statistic by
comparison with the distribution found by randomly
reallocating the order of the elements in one of the
matrices. |
| |
| zt
|
| zt is a
free software tool which performs simple and partial
Mantel tests. Contrary to the simple Mantel test, which
tests the correlation between only two matrices, the
partial Mantel test investigates the correlation between
two matrices while controlling the effect of a third one,
and thus tries to remove spurious correlations. The zt
software is written in the C programming language, both
for speed of computation and for being able to handle
very large matrices. The zt software is released under
GNU's global public license. |
| |
| Main
features |
- command line tool.
- written in C.
- huge matrices capabilities.
- speed of computations.
- simple text files as input data files.
|
| |
| Paper |
| The zt
paper gives a general introduction of the simple and
partial Mantel tests, describes the algorithm in detail
and finally describes some concrete examples based on
real datasets. You can freely dowload it at the Journal of Statistical Software, Vol.7, issue 10.
|
| |
| Download |
zt binaries have
been pre-compiled for different platforms. Source code,
description, examples and data files are always
furnished.
|
| Citation |
Eric
Bonnet & Yves Van de Peer (2002) zt: a software tool
for simple and partial Mantel tests. Journal of
Statistical software, vol. 7, issue 10: 1-12.
|
| |
| (c) 2000-2001 Eric Bonnet |
