The "Ideal" ordination method does not exist, but if it did it would possess the following qualities.

- It recovers gradients without
distortion.
- If clusters exist in nature,
this should be obvious in the ordination.
- It does not produce clusters
which do not exist.
- It gives the same result every
time for a given data set.
- There is a unique solution.
- Ecological similarity is
related to proximity in ordination space.
- Scaling of axes is related to
beta diversity.
- The method is not sensitive to
noise.
- "Signal" and
"Noise" are easily separated.
- You do not need to pre-specify
number of axes.
- The solution is the same, no
matter how many dimensions one chooses to look at.
- Unless by choice, all
sites/stands/quadrats are treated equally.
- The solution does not take much
computer time.
- The method is robust: it works
well for short and for long gradients, for low and high noise, for sparse
and full matrices, for big and for small data sets, for species-rich and
species-poor systems.
- For the mathematician: elegant.
- For the ecologist: available,
inexpensive, and easy to understand.

This
page was created and is maintained by Michael
Palmer.

To the ordination web page