It was Mike’s fidelity work.
OK I had another long session of reading, toggling and analysis on administering your advice and reduced stress to 0.1946. This is as low as I can get it.
I must admit to neglecting the value of the two way table. Never again. It was quite valuable in helping me gain a better understanding of the data. It is clear from the analysis that there is multiple sources of noise, with most of the noise coming from disturbance related factors (i.e. remnant size and vast array of past land uses including temporal variability). Unfortunately these factors represent truth in the area investigated, thus there is no escaping it.
The other noisy component of the data is the presence of a regional intergrade between at least 2 if not three vegetation communities. One could possibly interpret that as a signal, which is how I’m viewing it, as the presence of intergrades is natural and expected.
One last question. Should one report the resultant stress level? I would think that this is a responsible thing to do as it conveys to the reader the ‘strength’ of the analysis. It can also be used to demonstrate that the data patterns are quite complex, perhaps being an expected outcome?
Thanks for your pointers Lee and cheers till later.