Dear all,

I have a categorical variable with educational attainment (1-5) and want to do a statistical test for differnces on two different education variables.

I have one dataset and a dichotomous variable defining if someone has dropped out or not from a treatment programme. I want to test if there is a significant difference in educational attainment between these two groups. I have tried ttest edu, by(dropout) but this takes everything in one test. I need to see difference between educational attainment level 1 vs 1, level 2 vs 2 and so on.

Any thoughts on how to do this in practice?


Best regards,
Jonas.