Hello,

I am looking at the association between certain protective/risk factors and suicide in a sample of individuals with major depressive disorder. Data was collected from participants across 2 occasions and my data is currently in long format. I've run a mixed effects model using the following line of code:

Code:
 melogit suicide age i.ses i.sex_ social_support substance_abuse i.living_with || participant_ id:, or
Code:
 estat icc

Level ICC Std. Err. [95% Conf. Interval]
-------------------------------------------------------------------------------
subjectid .6436143 .0408226 .5602718 .7190809

I am just a little confused about how to interpret the icc. I understand that typically ICC indicates the proportion of total variance that is attributable to between cluster differences. So what does this mean when the clusters are individuals?

Moreover, what are the assumptions that need to be checked for melogit and how can I go about testing those.

Thank you,
Sam