1
$\begingroup$

I have run a Kruskal Wallis Test on my data and it is significant at p=0.00. I have currently reported the output as H (3) = 18.047, p<0.00. However, I now need to see where the difference between my groups lies, so ran pairwise comparisons. Here, looking at the adjusted significance there is a statistically significant difference between two pairs of groups (one at p=0.001 and the other p= 0.002)

My question is how do I incorporate these values into what I've already written. Is it a case of writing pairwise comparisons were conducted and then reporting the adjusted significance for each? And do I keep the original overall Kruskal Wallis significance?

Thanks for your help!

Improve this question
$\endgroup$

1 Answer 1

Reset to default
1
$\begingroup$

Yes, keep the overall test and then write that you conducted pairwise tests. I would do something like this (but I'd change the writing to relate it more to the data)

"A Kruskal-Wallis test showed that at there was a significant difference of means (H = 18.047, p <0.001). I then conducted post hoc tests to test pairwise comparisons. I found that group A was significantly different to group B (p = 0.001) and group C (p = 0.002). Groups B and C were not significantly different (p = 0.23)."

That would be my 'template answer'. I'd alter it to fit your data.

Improve this answer
$\endgroup$
2
  • $\begingroup$ Thank you so much for a quick response - very much appreciated! $\endgroup$
    – Dragonfly
    Commented Apr 1, 2017 at 11:46
  • $\begingroup$ No worries. If it answered your question feel free to mark this question as answered $\endgroup$
    – Conor Neilson
    Commented Apr 1, 2017 at 11:47

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.