This graph thinks the film-speed is a hair *higher*. I stand corrected: the amount of AA has no effect on speed.
That's the reason why I wanted to know at which level speed or other properties deviate by more substantial amounts. I assume you have the data right in front of you from the many experiments you have done by now. If you look at Pat Gainer's results (here and here), you shouldn't expect much difference even with big changes in AA amount.
Trying to be the best of whatever I am, even if what I am is no good.