This menu provides a range of distributions and models that can be used to
describe species abundance data. For the log-series, Poisson-log-Normal and
negative binomial distributions the species abundance data are grouped into
'octaves' using a logarithmic scale. These distributions are then fitted
using the DISTRIBUTION
directive using the octave classes. The geometric series, Zipf and
Zipf-Mandelbrot models are fitted to the observed abundance data using
the non-linear regression facilities. See the ECFIT procedure for
further details about the available distributions and models.
Data format
Specifies to format of the data for the plot. Select Single variate
to supply the individuals in a single variate. Alternatively, select
Multiple variates, if the data are to be
supplied in multiple samples of individuals.
Individuals
A variate containing the numbers of individuals per species.
Species
A variate containing the number of species for the associated number of individuals
in the corresponding element of Individuals. This field
can be left empty if each of the values in Individuals
corresponds to one species.
Groups
A factor specifying the groups for different samples.
Samples
For multiple samples this allows you to specify one or more variates containing the
individuals for different samples. Multiple selections can be transferred from the
Available data list by clicking the
button.
Model
Controls the distribution or model that is to be fitted to the data. You can choose from
Log-series, Poisson-log-Normal, negative binomial, Zipf, Zipf-Mandelbrot and Geometric series.
See the ECFIT procedure for
further details about the available distributions and models.
Available Data
This lists data structures appropriate to the current input field. The contents will change as you move from one field to the
next. Double-click on a name to copy it to the current input field; alternatively, you can type the name directly into the input field.
See Also