1
$\begingroup$

I want to compare two allele frequencies from two populations. I use Fisher's exact test for this. But I don't have the actual count of the alleles but just frequency. For eg: Frequency of Population(America) = 0.12, Population(Europe) = 0.23.

Can I just multiply both frequencies by 100 (like for America, 12 out 100 and Europe, 23 out of 100) and plug these values in Fisher's test function? Can some one please advise whether this is a right approach?

$\endgroup$
3
$\begingroup$

No, sample size is important, multiplying these numbers by say 10 or 1000 will produce vastly different results. You really need the actual counts for this. Otherwise you will have to use a different tool, such as a test of proportions (not true, also requires sample size).

$\endgroup$
4
  • $\begingroup$ Can you please explain what is the difference between a test of proportions and a Fisher's exact test. I thought Fisher's test is done when the values are small. $\endgroup$ – arshad Jun 17 '20 at 6:59
  • $\begingroup$ You should ask a new question about the difference between the two. Although in practice the Fisher's exact test is employed when sample sizes are small, it is valid for all sample sizes. $\endgroup$ – user2974951 Jun 17 '20 at 7:29
  • $\begingroup$ ok I will post a new question for that. But, as you advised "I should use a different tool".. can you kindly suggest any tool . $\endgroup$ – arshad Jun 17 '20 at 7:36
  • $\begingroup$ @arshad Without the sample size I cannot think of any tools. $\endgroup$ – user2974951 Jun 18 '20 at 9:49

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.