www.cmm.bristol.ac.uk/forum

I am using logistic regression model for three level, I successfully run model using runmlwin but after that, I want to estimate VPC for first, second and third level using some alternative method. please any one help me.

Note: I Know in discrete model such as logistic model variance is the function of mean or it is not free parameter but it is determined already by mean.

Hi Mahadev11,

The easiest approach would be to use the latent response method. Any good multilevel text book will describe this. You could also look at our free online course

Module 7: Multilevel Models for Binary Responses STATA Practical (p.18)

Essentially you calculate the VPC statistics in the usual way, except you set the level-1 variance to \pi^2/3 = 3.29 and you interpret these VPCs in terms of the propensity of the response occurring.


Best wishes

George