Within-group variation with ordinal dependent variable and cross-sectional data

[Giovanni Angioni]

Hi All,

I'm working with a cross-sectional dataset that has individual respondents (person_id) clustered into groups (group_id). I am trying to demonstrate that variation within groups on a variable of interest is significant, i.e. that individual respondents have different positions within groups, either visually or with tests or both. The variable of interest (ordinal_var) is ordinal and it goes from 1 to 5. The number of groups is large (150).
All techniques I could find work with continuous variables or with longitudinal data.
The dataset looks like this:

* Example generated by -dataex-. For more info, type help dataex
clear
input byte(person_id group_id ordinal_var)
 1 1 2
 2 1 2
 3 1 3
 4 1 1
 5 2 4
 6 2 2
 7 2 1
 8 2 3
 9 2 5
10 3 5
11 3 4
12 3 2
13 3 1
14 3 3
15 4 1
16 4 1
17 4 2
18 4 2
19 5 3
20 5 4
end

I would really appreciate your help on this. Many thanks!