Question on Fisher's Exact Test

[Mathwizard6254]

Hey all, hope everyone had a great thanksgiving. I was wondering if anyone could explain to me what the Fisher's Exact Test is about and how to use it. Thanks!

 

[Dr.ThinkDeep]

At the elementary level consider a two parallel-group double-blind trial with binary outcome just prior to the unblinding.
Let us call
A the number of responder patients treated with verum
B the number of responder patients treated with placebo
C the number of nonresponder patients treated with verum
D the number of nonresponder patients treated with placebo

You know that A+B patients responded to the treatment and B+C did not.
You know that A+C patients were treated with verum and B+D were treated with placebo.

Given these marginal row and column totals, you compute a probability to find certain numbers A B C D und assumption of the hypothesis
H0: placebo and verum did not make a difference.
(Just like taking out (without replacement) A+B balls from an urn known to contain A+C white balls and B+D black balls initially.)

Now unblind yourself and sum up all probabilities that are equal or lower than assigned to the combination A B C D which you have found.
This sum of probabilities is your exact p-value, i.e. the probability that your result or one that is even less probable has occurred by chance given that verum or placebo do not matter.

I did not take the time to make this shorter but I do not know on what level to argue yet.

 

[tacman]

Hi there, the Fisher's Exact Test is a statistical test used to determine the significance of the relationship between two categorical variables. It is commonly used when the sample size is small and the assumptions of other tests, such as the chi-square test, are not met. It calculates the probability of obtaining the observed data or more extreme results, assuming that the null hypothesis is true.

To use the Fisher's Exact Test, you first need to create a contingency table with the observed frequencies of the two categorical variables. Then, you can use a statistical software or a calculator to calculate the p-value. If the p-value is less than the chosen significance level, typically 0.05, then we reject the null hypothesis and conclude that there is a significant relationship between the two variables.

I hope this helps! Let me know if you have any further questions. Happy Thanksgiving!