🚀 go-pugleaf

In article <3haqjg$jo1@knot.queensu.ca>, dower@biology.queensu.ca (John Dower) writes:
> Hello...guess my subject line says it all.  I'm looking for IBM-based software package for doing Mantel
> tests.  I've been using something called the "R-packeage" from Pierre Legendre's lab at the
> University of Montreal.  It's a Mac-based routine, but I've recently lost access to the Mac I'd been using
> (and would really prefer to find something I can run on my IBM anyways).  
> 
> Any suggestions?
> 
> Thanks in advance.
> 
> John Dower

According to Fortin & Gurevitch (Mantel tests:  spatial structure in field
experiments, pp 342-359 in SM Scheiner & J Gurevitch (eds), Design and
Analysis of Ecological Experiments, Chapman & Hall, 1993), the Mantel
(two-matrix) statistic can be computed using the MXCOMP program of the
NTSYS-pc package (version 1.6 and higher) for IBM and compatibles.
NTSYS is marketed by Exeter Software (100 North Country Rd, Setauket
NY 11733); also BFJ Manly (1991, Randomization and Monte Carlo Methods
in Biology, Chapman & Hall) provides FORTRAN subroutines to carry out
the Mantel (two-matrix) statistic (MANT2), as well as a test for three
matrices (MANCOR) based on Manly's regression approach.  They also say
that the R program is available without cost in CMS(IBM), VMS(VAX) and
Mac version; perhaps you could acquire source code and modify for a
PC compiler.  They give the following address for P Legendre:
Departement de sciences biologiques, Universite de Montreal,
C.P. 6128, Succursale A, Montreal, Quebec, Canada H3C3J7).

Just yesterday, I consulted with a student who plans to use Mantel tests.
I'd like to know what you find in the way of IBM programs.

Best wishes,
Susan Durham
<sdurham@cc.usu.edu>
Department of Fisheries and Wildlife
Utah State University
Logan, UT 84322-5210