# What type of multiple comparisons is used in multcompare?

5 views (last 30 days)
Eric on 21 Aug 2016
Edited: Lingyun GUO on 10 Jul 2020
Hi everybody,
I've used the following function after performing Kruskal Wallis test:
c = multcompare(KW_stats(1,1).name)
Does anyone know what type of multiple comparisons is used? FDR, Bonferroni?
Best,
Eric

Qu Cao on 23 Aug 2016
Edited: Qu Cao on 23 Aug 2016
Hi Eric,
You can specify the type of comparison as documented at the following link:
The default type is 'tukey-kramer'.
Thanks,
Qu
Lingyun GUO on 10 Jul 2020
Edited: Lingyun GUO on 10 Jul 2020
Dear Cao:
I have 3 sets of data. It has been organized into two columns The first column is basedata; The second column is the grouping basis.
G1(:,1)=rand(30,1);
G1(:,2)=1;
G2(:,1)=rand(32,1);
G2(:,2)=2;
G3(:,1)= rand(30,1);
G3(:,2)=3;
X=[G1;G2;G3]; % size is (92*2).
[P,anovatab,stats] = kruskalwallis(X(:,1),X(:,2));
c2=multcompare(stats);
1 2 -18.21 -2.31 13.60 0.94
1 3 -11.96 4.20 20.36 0.82
2 3 -9.40 6.51 22.41 0.60
In order to verify that the data is accurate, I continued to carry out two separate KW test data.
A= [G1;G2];
[P,anovatab,stats] = kruskalwallis(A(:,1),A(:,2));
c2=multcompare(stats);
1 2 -10.34 -1.35 7.63 0.77
Got the p value of their difference. Why, Which p value can truly reflect the difference between G1 and G2?