Tsung Fei Khang --

>
> If the expectation of the empirical estimator for mean p-value is a function
> of the number iterations that becomes asymptotically unbiased, then this
> would explain the simulation results  (attachment in the original posting),
> since for small number of iterations, some bias would remain, and only
> disappear (hence the "stabilization" feeling) when number of iterations is
> large.
>
> Thanks again for all for clarifying the issue.

The issue didn't get clarified if that's the conclusion.   In a
permutation test each replicate is independent and equivalent to a
coin toss.

Thus the estimate of P is unbiased, not asymptotically unbiased.

Joe
----
Joe Felsenstein         [email protected]
 Department of Genome Sciences and Department of Biology,
 University of Washington, Box 355065, Seattle, WA 98195-5065 USA

-- 
MORPHMET may be accessed via its webpage at http://www.morphometrics.org

To unsubscribe from this group and stop receiving emails from it, send an email 
to [email protected].

Reply via email to