On 2 Dec 1999 06:51:52 -0800, [EMAIL PROTECTED] (Robert Dawson)
wrote:
> Rich Ulrich asks:
>
> > - Is there any reason not to treat the 50 plots with 1 seed as if it
> > were "1 plot with 50 seeds"? - to be compared to the other 10 plots
> > with 50 seeds. And 10 with 25 seeds. Off hand, I don't think of any
> > reason.
>
> Spatial variation in soil quality, lighting, etc. ?
Yeah, I guess you might try to treat them separate, if there were
extra variables like those.
There is some potential for pitfalls in experimental design, in
addition to being the need for (dubious?) assumptions, when we try to
combine (or contrast) many-small-groups with a-few-large-groups, any
time. When one criterion is a dichotomy (Yes/No for N=1), the
contrast seems more awkward that dealing with count vs count.
The latter still seems reasonable for the problem as it was posed.
--
Rich Ulrich, [EMAIL PROTECTED]
http://www.pitt.edu/~wpilib/index.html
