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

Add a procedure to compare all pairs of proportions after a Y by X chi square analysis

What inspired this wish list request? 

In my research I often have to compare different experimental conditions for their proportions (mortality for instance). I can perform a chi square test with the Y by X plateform with the Treatments in the X, the parameter in the Y (living vs dead) and the count as Freq. I obtain a global p-value but then I can't discriminate treatments.

 

What is the improvement you would like to see? 

I would like to have a post hoc procedure to hava a multiple two-samples proportions test in order to test all pairs along with a connecting letters report. Ideally a correction for multiplicity (as Tukey) would be needed. I've been using another stat tool with the Marascuilo procedure.

 

Why is this idea important? 

It will be important for all situations where there are more than two groups to compare for their proportions