Comparing and classifying communities
because both sites were unsuitable.
When numbers of sites or habitats are to be compared the
offered by CAP can form the basis of cluster analysis, which seeks to identify
groups of sites, or stations that are similar in their species composition.
Classification methods comprise two principal types, hierarchical, where objects
are assigned to groups that are themselves arranged into groups as in a
dendrogram, and non hierarchical, where the objects are simply assigned to
groups. The methods are further classified as either
analysis proceeds from the objects by sequentially uniting them or
where all the objects start as members of a single group which is repeatedly
divided. For computational and presentational reasons hierarchical agglomerative
methods are the most popular.
The basic computational scheme used in cluster analysis can be illustrated using
single linkage cluster analysis as an example. This is the simplest procedure and
consists of the following steps.
Start with n groups each containing a single object (sites or
Calculate, using the similarity measure of choice, the array of
between object similarities.
Find the two objects with the greatest similarity, and group them
into a single object.
Assign similarities between this group and each of the other objects
using the rule that the new similarity will be the greater of the two
similarities prior to the join.
Continue steps 3 and 4 until only one object is left.
The results from a cluster analysis are usually presented in the form of a
The problem with all classification methods is that there can be no objective
criteria of the best classification; indeed even randomly generated data can
produce a pleasing and convincing dendrogram. Always consider carefully
whether the groupings identified seem to make sense and reflect some feature of
the natural world.
Multivariate analysis is used when the objective is to search for relationships
between or classify objects (sites or species) that are defined by a number of
attributes. Generally, we seek to show the relationship between sites (or samples)
using the species as the attributes. Data sets can be large, for example marine
benthic or forest beetle faunal studies can easily require analysis of a matrix of
100 samples (stations) by 350 species and thus multivariate analysis requires a
computer. If the objective is to assign objects to a number of discrete groups then
cluster analysis should be considered. If there is no
reason to believe the
objects will or could naturally fall into groups then an ordination technique may be
more suitable. Ordination assumes the objects form a continuum of variation and
the objective is often to generate hypotheses about the environmental factor(s)
Copyright 2004, PISCES CONSERVATION LTD