>
> Judy
>
> Your comment about keeping things as simple as possible is correct. This
Oops Wayde, I think that's Occam's razor not me. "Simple as possible" was
what I was saying isn't true. That's Occam's Razor "wisdom" ... and almost
by definition wrong... What I meant, even if I didn't say so explicitly,
was ways to keep the testing from reaching the point of diminishing
returns.
I do like testing (to quote myself: a test never fails, it ALWAYS gives
you information), but within reason... let it be meaningful and
productive, not ad infinitum... as Dave notes when he outlines 512
possible variables. And *still* you might feel frisky that day & press
harder on the brush & there go the 512... (There *is* no absolute control,
anywhere.)
Judy
> oversimplify an experiment to the point that it is meaningless.
> Essentially this is what the gum-pigment ration test did. Why ... because
> each of the variables depend on each other. If they didn't then the test
> would in fact be valid.
>
> Designing experiments to deal with correlated or depedendent variables is
> simply not an easy thing to do.
>
> - Wayde
> (wallen@boulder.nist.gov)
>
>
>