T test and median

TO DO: the association between life expectancy (le tot) and some socio-economic variables in the European regions.
Dichotomise the variable le tot in this way:
􏰂0 if le toti ≤ median(le tot)
1 otherwise for each observation I;
How to do the t test but with median?

If you are testing the significance bewtween two medians, I don't believe a t test is appropriate. Look into Mood's test and Kruskai-Wallis.

This topic was automatically closed 21 days after the last reply. New replies are no longer allowed.

If you have a query related to it or one of the replies, start a new topic and refer back with a link.