Correlated random effects

[Saeideh Shahi]

Hi everyone

I am estimating a mixlogit model using 11 random variables. How can I estimate correlated random effects? would you please help me with the codes?
Here is my mixlogit syntax:

mixlogit choi, group(idqub) id(id) rand(d2 d3 d4 d5 d6 d7 d8 d9 d10 d11 d12) (d1 is reference alternative)

This is for a Best-Worst scaling (BWS) model that have 12 objectives and no attribute level.

Many thanks
Saeideh

[Phil Bromiley]

See:

The Stata Journal Volume 13 Number 1: pp. 65-76

Subscribe to the Stata Journal

Within and between estimates in random-effects models: Advantages and drawbacks of correlated random effects and hybrid models

Reinhard Schunck Department of Sociology University of Bielefeld Bielefeld, Germany [email protected]