calculate a P value using a permutation test

How can I calculate a P value using a permutation test for these 2 groups?

controlA=[0.22, -0.87, -2.39, -1.79, 0.37, -1.54, 1.28, -0.31, -0.74, 1.72, 0.38, -0.17, -0.62, -1.10, 0.30, 0.15, 2.30, 0.19, -0.50, -0.09];

treatmentA=[-5.13, -2.19, -2.43, -3.83, 0.50, -3.25, 4.32, 1.63, 5.18, -0.43, 7.11, 4.87, -3.10, -5.81, 3.76, 6.31, 2.58, 0.07, 5.76, 3.50];

I know that both samples come from the same distribution.

thanks

[Shuting Li]

permutationTest(controlA, treatmentA, 10000, 'plotresult', 1);

and the permutation code is in https://github.com/lrkrol/permutationTest.git

Answer 1

[Star Strider]

In MATLAB, use the ranksum function.

For your data:

p =
         0.350702223666955

h =
   0


stats = 
       zval: -0.933228071880792
    ranksum: 375

So the ‘p’ value indicates that they are not significantly different, and ‘h’ indicates that the null hypothesis is not rejected.

[noa goldman]

Thank you very much, but you calculated it using the Wilcoxon test and I have to program it using the permutation test.

[Star Strider]

I have never heard of the ’permutation test’. When I did an Interweb search on it, the Wilcoxon rank-sum test came up in several examples. That is the reason I use it here.

[BINNAN YU]

permutation test is equivalent to wilcoxon rank-sum test, but two are different test

Answer 2

[Jeff Miller]

This contribution on file exchange looks like it will do what you want.