Heike Link posted on Tuesday, August 12, 2014 - 1:08 am
I have estimated a hybrid discrete choice model which consists of a conventional binary logit model and a latent variable part. Both parts where estimated jointly by using MLR with Monte Carlo simulation. The structure of my model is below:
Y ON x1-x5 (Y is a binary variable, x1-x5 are continuous predictors) Y ON LV2 LV1 BY i1 i2 (i1 and i2 are continuous indicators) x6 x7 ON LV1 (x6, x7 are exogenous variables, continuos) LV2 BY i3 i4 i5 i6 (i3 – i6 are categorical indicators) x8 x9 ON LV2 (x8, x9 are exogenous variables, continuous) LV2 ON LV1.
The model was aimed at providing a better explanation of Y by including latent variables and this worked out well, the parameters are significant and can well be interpreted.
I am now asked by a referee to introduce unobserved consumer heterogeneity. This means that I need to estimate a Mixed Logit model by allowing some parameters to be random, based on assumed heterogeneity distributions such as normal or lognormal.
Does Mplus allow estimating a Mixed Logit model which contains also the latent variable part as my model above? Is it possible, for example, to estimate random parameters for Y ON x1-x5 within the hybrid model listed above?
If the random effect parameters are identified they can be estimated in Mplus. For example, to add a normally distributed random intercept for Y, just say
f BY y;
which means that f is the random intercept and its variance is the variance of f.
Our website has related discrete-choice papers posted under Papers, Miscellaneous, such as
Temme, D., Paulssen, M., & Dannewald, T. (2008). Incorporating latent variables into discrete choice models – A simultaneous estimation approach using SEM software. BuR – Business Research, 1, 220-237. download paper contact first author show abstract