cancel
Showing results for 
Show  only  | Search instead for 
Did you mean: 
Choose Language Hide Translation Bar
0 Kudos

Fit model for a non-parametric test

Good day,

I would like an ANOVA equivalent for a non-parametric test.

I understand that to do this there are several options in JMP, one which is the The Kruskal-Wallis test, however, is it possible to have a two/three way type of ANOVA in the case of a parametric test that we do using the Fit model 

Also, when I try using the Fit Y by X option using Steel-Dwass there are no option for connecting letters. (I see a lot of people have requested for this option on JMP, is there by any way a solution yet? I would really appreciate one).

3 Comments
SamGardner
Level VII

For multi-way non-parametric ANOVA, there are a few options available, including Friedman's test (which just doing an ANOVA on the the ranked observations).  Another is to use quantile normalization, where you use the quantile of the data and convert that to the equivalent normal distribution value.  But, one challenge is that there is not an generally good accepted way of doing this.

 

For the non-parametric multiple comparisons in the Bivariate platform under Fit Y by X, we will consider adding connected letter reports to the output.  

 

Thank you for your input and suggestion. 

 

mia_stephens
Staff
Status changed to: Acknowledged

Changing the status to acknowledged. Thank you.

mia_stephens
Staff
Status changed to: Yes, Stay Tuned!