Question

When you do a Kruskal Wallis test, why do you always use a right tail test?

Answer 1

kruskal wallis test:-

The Kruskal–Wallis test by ranks, Kruskal–Wallis H test(named after William Kruskal and W. Allen Wallis), or one-way ANOVA on ranks is a non-parametric method for testingwhether samples originate from the same distribution. It is used for comparing two or more independent samples of equal or different sample sizes.

A huge Kruskal– Wallis test shows that something like one example stochastically overwhelms one other example. The test does not distinguish where this stochastic predominance happens or for what number of sets of gatherings stochastic strength acquires. For examining the particular example sets for stochastic strength, Dunn's test,[5] pairwise Mann-Whitney tests without Bonferroni correction,[6] or the more ground-breaking however less outstanding Conover– Iman test[6] are now and then utilized.

Since it is a non-parametric strategy, the Kruskal– Wallis test does not accept a typical circulation of the residuals, not at all like the similar to one-path examination of difference. On the off chance that the specialist can make the presumptions of an indistinguishably molded and scaled dispersion for all gatherings, with the exception of any distinction in medians, at that point the invalid speculation is that the medians of all gatherings are equivalent, and the elective theory is that no less than one populace middle of one gathering is unique in relation to the populace middle of no less than one other gathering.