I saw from their Wikipedia page, and my impression is that both are developed when the data is nested. Are multilevel model and random effect model the same concept? If they are not, what are their differences and relations? Thanks!

  • Random effect is a very vague term, that means different things to different people. But yes, they can be the same. – Jeremy Miles Jul 31 '13 at 16:27
up vote 1 down vote accepted

Yes, to quote the Wikipedia page on multilevel model:

Multilevel models (also hierarchical linear models, nested models, mixed models, random coefficient, random-effects models, random parameter models, or split-plot designs) are statistical models of parameters that vary at more than one level.1

It naturally arises from observing the hierarchical and the clustered structure of the collected data typical found in treatment comparisons in clinical trials. It allows modelling residuals at different level, in other words, between-groups and within-group components for a two-level model.

I just re-iterated something that I learnt in my course, I could expand a bit on this if needed :)

Your Answer


By clicking "Post Your Answer", you acknowledge that you have read our updated terms of service, privacy policy and cookie policy, and that your continued use of the website is subject to these policies.

Not the answer you're looking for? Browse other questions tagged or ask your own question.