.

Bonferroni works the same for parametric or non parametric tests

it just cares about the familly wise error rate, that is the output of a set of tests, not which kind of statistical test you are using

https://en.wikipedia.org/wiki/Bonferroni_correction

.

Yes and Yes.

PS: there is no such thing like "non-parametric data". Data subject to statistical analyses is numerical, and it may either be discrete or continuous. What you mean is presumably that the (conditional) frequency distribution of the data can not be described well by some known parametric probability model.

Fabrice and Jochen are correct.

Thanks all for the input. I mean non-parametric test instead of data.

Please let me know if these references/sites are useful to you:

1.  Multiple Comparisons in Nonparametric Tests - The Analysis Factor

www.theanalysisfactor.com/multiple-comparisons-in-nonparametric-tests/Cached

Bonferroni correction is your only option when applying non-parametric statistics (that I'm aware of). Or, actually, any test other than ANOVA. A Bonferroni correction is actually very simple. Just take the number of comparisons you want to make, then multiply each p-value by that number.

2.  Which Statistical test is most applicable to Nonparametric

...

https://www.researchgate.net/.../Which_Statistical_test_is_most_applicable_to_Nonpar...

It seems SPSS also provides some nonparametric tests for this (haven't ... Dear Sheejamol, you can use Bonferroni correction for multiple comparisons . ... For post hoc tests, Mann-Whitney U Test, is good, But, with a correction to adjust for the ...

3.  Bonferroni correction on multiple Kruskal-Wallis tests - Cross ...

https://stats.stackexchange.com/.../bonferroni-correction-on-multiple-kruskal-wallis-te...Cached

Jan 14, 2015 - You would not use the Bonferroni adjustment on the Kruskal-Wallis test itself. The Kruskal-Wallis test is an omnibus test, controlling for an overall false-positive rate. You would use the Bonferroni for post hoc Dunn's pairwise tests. Indeed, Dunn introduced the "Bonferroni" adjustment.

4.  A more sophisticated Bonferroni adjustment

privatewww.essex.ac.uk/~scholp/bonferroni.htmCached

Do a relevant paired test for each pair (e.g. t test, Mann-Whitney, Wilcoxon) and adjust the sig values with a Bonferroni adjustment. NB it is not permitted to do a ...

Dennis

Dennis Mazur

Hi Dennis, thanks for the explanation. However, I could not access the links given. Could you please resend it? Thanks!

Adjustment for multiplicity applies for nonparametric tests as well as parametic tests.