Variance & Eigenvalues
For both Redundancy Analysis and Canonical Correspondence Analysis this tab
presents tabulated data for the eigenvalues of each axis and the amount of variance
present in the original data that is accounted for by the axis. It also gives summary
information on your data set.
The total variance or what is more strictly termed inertia is the sum of the canonical
and non canonical Eigen values.
The output is explained below.
Number of sites This is the number of columns in the Sample/Species array loaded
as the biological file. It may be the number of transects, quadrats, pitfall traps etc.
Number of species This is the number of rows in the Sample/Species array loaded
as the biological file. It is the total number of taxa in the data set.
Number of environmental variables This is the number of rows in the
Environmental array loaded as the biological file. It is the total number of taxa in the
Number of canonical axes This is the number of axes that can be related to
Number of non canonical axes This is the number of axes that hold the residual
variance unexplained by a linear combination of the environmental variables.
Total variance This is the sum of the variance explained by the canonical and non
Canonical Eigenvalues These are the eigenvalues for the canonical axes.
% variance explained This is the amount of the total variance in the data that is
explained by each of the canonical axes.
Cumulative % variance This is the sum total of the variance explained by the
addition of each new canonical axis.
Multiple correlation species/environment scores The analysis produces scores
for each site based on either their environmental variables or species composition.
This row gives, for each canonical axis, the correlation between these two scores for
all the sites. The value presented is the multiple correlation coefficient produced by a
Copyright 2004 PISCES Conservation Ltd