mxplot: Matrixplot of groups similarities

In dave: Functions for "Data Analysis in Vegetation Ecology"

Description

This calclulates and plots average similarities of rows (releves) in a square, classified matrix. Correlation coefficient is used as similarity, upon plotting proportionas to the surface of circles. Hence, diagonal elements exhibit similarity of groups, off-diagonals all similarities to the remaining groups.

Usage

mxplot(veg, rmember, use, y=1, ...)
matrixplot(veg, rmember, use, y=1)

## Default S3 method:
mxplot(veg, rmember, use, y=1,...)
## S3 method for class 'mxplot'
plot(x,...,capacity=100)

Arguments

veg	This is a vegetation data frame, releves are rows, species columns
rmember	Group membership of the rows or columns, typically taken from cluster analysis
use	Either "rows" or "columns"
y	Transformation of species scores: x'= x exp(y)
...	Capacity. Adjusts plot size to the number of groups.
x	An object of class "mxplot"
capacity	The number of group symbols that fit on one page

Details

The distance measure used is "correlation used as distance". See reference.

Value

An object of class "mxplot" with at least the following items:

order	Dimension of the similarity matrix (equal to the number of groups ng)
mmatrix	The ng x ng matrix of average group similarity
levels	The ng group names (a vector of character variables)

Note

Plot parameter capacity only affects the format of plot. Just try.

Author(s)

Otto Wildi

References

Wildi, O. 2017. Data Analysis in Vegetation Ecology. 3rd ed. CABI, Oxfordshire, Boston.

Examples

# Starts with classifying releves by cluster analysis
dd<- vegdist(sveg^0.5,method="euclid")         # dd is distance matrix
o.clust<- hclust(dd,method="ward")             # clustering
groups<- as.factor(cutree(o.clust,k=6))        # forming 6 groups

o.mxpl<- mxplot(sveg,groups,use="rows",y=0.5)
plot(o.mxpl,capacity=30)

Example output

Loading required package: cluster
Loading required package: labdsv
Loading required package: mgcv
Loading required package: nlme
This is mgcv 1.8-33. For overview type 'help("mgcv-package")'.
This is labdsv 2.0-1
convert existing ordinations with as.dsvord()

Attaching package: ‘labdsv’

The following object is masked from ‘package:stats’:

    density

Loading required package: vegan
Loading required package: permute
Loading required package: lattice
This is vegan 2.5-7
Loading required package: nnet

Attaching package: ‘nnet’

The following object is masked from ‘package:mgcv’:

    multinom

Loading required package: tree
The "ward" method has been renamed to "ward.D"; note new "ward.D2"
Call:
mxplot.default(veg = sveg, rmember = groups, use = "rows", y = 0.5)

dave documentation built on May 2, 2019, 1:30 p.m.