I would like to clarify that I recognise that such conditions do not belong to Fisher's Exact test as originally stated. I am sorry if I should have said so in my original post.
Hello
I would be very grateful for advice on conditions for use of Fisher's Exact test (and generalizations of this test beyond the 2 x 2 case). I am specifically interested in finding out where the condition that less than 80% of expected counts are of size at least 5 originated from exactly. I am looking for a literature source to confirm this, please. I would also be keen to learn of any variants of this condition that group members can point me to in the literature.
Thanks in advance
Best wishes
Margaret
The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336.
You may leave the list at any time by sending the command
SIGNOFF allstat
to [log in to unmask], leaving the subject line blank.
|