www.cmm.bristol.ac.uk/forum

Hello everyone,

I'm a new user of MLwiN and multilevel modelling too. I am writing because I need your insights about a 3-level model, which the dependent variable is dichotmous (0=low achievers, 1=resilient). When i discussed about this analysis with some of my colleagues, they suggested to me to try the logistic regression for binary response. Trying this analysis and put only 2 predictors to level 2, i saw that it takes a lot of time to run the equation and i think that i'm doing something wrong. Is there an other option to run a model like this, with a dichotomous dependent variable? Or it is right the suggestion for binary response? I really hope to help me and finally to find a solution because i should had already run this analysis but i'm not sure if i follow each step right and in addition if it's normal to take so many time!

Kind regards,
Mara

These types of model are covered in the following places:

• Chapter 9 of the MLwiN User Guide (http://www.bristol.ac.uk/cmm/media/soft ... al-web.pdf)
• Chapter 10 of the MCMC Guide (http://www.bristol.ac.uk/cmm/media/soft ... mc-web.pdf)
• Module 6 (single level) and Module 7 (multilevel) of the LEMMA online course (https://www.cmm.bris.ac.uk/lemma/)

I would suggest working through these to become familiar with using the software on these types of model and to get an idea of what options are available.

Thank you! I will check out the links.