Fisher test and exact test
0
1
Entering edit mode
8.2 years ago

Hi guys,

What is

P-VALUE CORRECTED WITH FDR by Exact test

P-VALUE CORRECTED WITH FDR by Fisher test?

When should we use these parameters?

R RNA-Seq gene • 4.8k views
ADD COMMENT
1
Entering edit mode

What you're asking is unclear. An exact test can be any sort of test in which the test statistics doesn't rely on an approximation. Fisher's test can mean either Fisher's exact test or Fisher's combined probability test which is also known as Fisher's method of combining p-values. Neither of these is a p-value correction method. Fisher's method is a way of combining p-values to test the meta null hypothesis that the null hypothesis is true for all the individual experiments. A FDR-corrected p-value is a p-value that has been corrected for multiple testing with a procedure that controls the false discovery rate (i.e. the expected proportion of false positives).

ADD REPLY
0
Entering edit mode

What kind of data are you analyzing? Or is it a home work assignment?

ADD REPLY
0
Entering edit mode

RNA-seq analysis,I did differential experssion and now I want to do meta analysis,but my prof. Said for determination of parameters,Calculate these p-value for some experemints.

ADD REPLY
1
Entering edit mode

Can't your Prof. Said explain to you what he means? Because Fisher's test IS an exact test!?!

ADD REPLY
0
Entering edit mode

Really!At first I thought he means fisher exact test.anyway,why should I do it before meta analysis?

ADD REPLY
0
Entering edit mode

Aren't they one and the same?

ADD REPLY
0
Entering edit mode

I think they are different.as I explain above my prof. Said.

ADD REPLY
0
Entering edit mode

I suspect that there's some confusion between "Fisher's exact test" and "Fisher's method", which is a method of combining p-values for things like a meta-analysis. You might ask your prof. if that's what he/she means.

ADD REPLY
0
Entering edit mode

Thank you Devon,I can not ask him now,he is on a trip.is it routine doing fisher exact test in this situation?if not,I should do "fisher's method".

ADD REPLY
1
Entering edit mode

You should use Fisher's method, since you already have p-values from the different experiments (I assume). This is very likely what he was trying to convey.

ADD REPLY

Login before adding your answer.

Traffic: 2723 users visited in the last hour
Help About
FAQ
Access RSS
API
Stats

Use of this site constitutes acceptance of our User Agreement and Privacy Policy.

Powered by the version 2.3.6