2 3 5
2 2 4
2 1 0
3 5 1
3 4 20
3 3 10
3 2 3
3 1 3
4 5 2
4 4 14
4 3 3
4 2 2
4 1 1
5 5 6
5 4 7
5 3 5
5 2 0
5 1 1
6 5 10
6 4 76
6 3 15
6 2 4
6 1 1
;
create one observation per
subject, ;
using the frequency variable
totsubj ;
data a(drop=totsubj);
set a;
do i = 1 to totsubj;
output;
end;
**;
** kruskal-wallis test ***;
**;
proc nparlway data=a wilcoxon;
class group;
var response;
title 'Kruskal-Wallis test -
looking at type of student and
perceived success
run;
Figure 12: Program for
Kruskal-Wallis test for
data in the form of
frequencies (contingency
table)
Appendix 380