Why does mattest output different p-values when using bootstrapping?

1 view (last 30 days)
Andy
Andy on 11 Jun 2015
Commented: Sreeja Banerjee on 12 Jun 2015
If I use the following code
a=[1:20,1:20]
b=[2:21,2:21]
pvalues1=mattest(a,b,'Bootstrap',1000)
pvalues2=mattest(a,b,'Bootstrap',1000)
pvalues1 does not equal pvalues2, however pvalues1(1)==pvalues1(2) or pvalues2(1)==pvalues2(2)
Why does this behaviour occur?
  1 Comment
Sreeja Banerjee
Sreeja Banerjee on 12 Jun 2015
Hi Andy,
Which release of MATLAB are you using? Also what values do you get for pvalues1 and pvalues2? I think the data is ill-formed because I am not able to reproduce the same behavior.

Sign in to comment.

Sign in to answer this question.

Answers (0)

Categories

Find more on Analysis of Variance and Covariance in Help Center and File Exchange

Tags

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!