Ronald Bloom wrote:
>
> In sci.stat.consult Elliot Cramer <[EMAIL PROTECTED]> wrote:
> > In sci.stat.consult Ronald Bloom <[EMAIL PROTECTED]> wrote:
> > Herman as usual is absolutely correct; the validity of the Fisher test is
> > analagous to the validity of regression tests which are derived
> > conditional on x but, since the distribution does not involve x, are valid
> > unconditionally even if the x's are random.
>
> If I take your analogy in the direction that leads back to
> the Fisher test, I should be able to paraphrase the above as
>
> "the validity of the [Fisher test] which [is] derived conditional
> on [the fixed marginals] but, since the distribution does not
> involve [the fixed marginals], [is] valid unconditionally even
> if the [marginals] are random.
>
> Please clarify what is meant by "the distribution does not
> involve [the fixed marginals]". I am not clear on this:
> the Fisher test statistic (hypergeometric upper tail probability)
> certainly *does* depend on the fixed marginals in this
> case -- they appear in every term in that tail sum.
Usual the assumptions for Fishers exact test are not true.
What you can fix are the row margins, or column margins or grand total
or
Element of row i and column j.
In these cases the exact Fisher test is biased.
At least in Survo (may be in some other programs too) it is possible
make the test also in these cases. Look at
http://www.helsinki.fi/survo/q/qu1_03.html
regards
Juha
--
Juha Puranen
Department of Statistics
P.O.Box 54 (Unioninkatu 37), 00014 University of Helsinki, Finland
http://noppa5.pc.helsinki.fi
=================================================================
Instructions for joining and leaving this list and remarks about
the problem of INAPPROPRIATE MESSAGES are available at
http://jse.stat.ncsu.edu/
=================================================================
