Worked Example

84

13

Worked Example

This Section gives an example of the use of ECOM. It is based on the well known Dune

Meadow data  set used by Jongman et al. (1995).

The objective of the analysis is to determine if  there any gradients in the species data

that can be explained by the environmental variables.

The data files are supplied with the ECOM installation.

First open the species abundance file using the Biological File drop down menu. This

file holds the dependent variables and is named Dune_species.csv.

Now open the file of environmental variables using the Environmental File drop down

menu. This file holds the independent variables that may influence species abundance

and is named Dune_enviro.csv.

We will now take you through the stages of a typical Canonical Correspondence

Analysis. The purpose of this analysis is to identify the environmental variables that

are most important in moulding the plant community. The stages of this process are

described in turn below.

Preliminary inspection and data transformation

Examine and Select Environmental Variables

Interpreting the results

13.1

Preliminary inspection and data transformation

Having opened the data sets the species and environmental data will be presented in

grids. The raw species and environmental data is viewed by clicking on the

Sample/Species Data and Environmental Data tabs respectively. The data sets

can be changed and transformed from the working data tabs.

Changes made to the working data will not change the raw data.

We will not undertake any transformations on the Dune Meadow data set. This is

because the numbers in both the environmental and species data sets are both with a

single order of magnitude.

We can find out about the range in our data using the Summary tab. Below it can be

seen that the largest maximum environmental variable value is 11.5 and the smallest

is 1. A similar inspection should be undertaken on the species data.

Copyright 2004  PISCES Conservation Ltd