[From Bruce Gregory (991010.1646 EDT)]
>That Powers cannot understand that his approach should be rejected is his
>problem not mine.
The only way _I_ can tell if Powers is wrong and you are correct is to
compare the predictions of your model and his. I am familiar with his model.
What does your model predict? How have you tested its predictions? How much
of the variance does your model explain. (Powers' model explains roughly
99%, but it needs to be tested on your data.)
Bruce Gregory