[Limdep Nlogit List] introducing socio-economic characteristics in binary choice experiments

Mikołaj Czajkowski miq at wne.uw.edu.pl
Thu Jan 22 21:21:34 EST 2009


Rady Talaat wrote:
> Hello,
> For the binary unlabeled experiments, how can I incorporate the individual characteristics in the model? Although they may be introduced as interactions with the attributes to avoid hessian singularities, this inclusion of the separate attributes along with their interaction is likely to induce multicollinearity.   

Dear Rady,

You could try other models, e.g. Error Component Model with 
heterogeneity in the variances of the error components, Covariance 
Heterogeneity Nested Logit or Random Parameter Logit. See NLogit manual 
and the literature for details.

Best regards,

-- 
     Mikolaj Czajkowski

     Warsaw Ecological Economics Center
     University of Warsaw
     http://www.woee.pl/



More information about the Limdep mailing list