[Limdep Nlogit List] latent class model and RPL

[William Greene]

The implausibly large coefficients, with large standard errors, probably
indicate that your
LCM has too many classes.
/B. Greene

On Tue, Dec 6, 2022 at 12:07 AM Elias José Gordillo Chávez via Limdep <
limdep at mailman.sydney.edu.au> wrote:

> I analyzed the preferences of farmers toward 4 attributes and ran several
> models. The first one was a mixed model, in which, according to their
> standard deviation, some attributes indicate heterogeneity in people's
> preferences. With this in mind, I ran a latent class model of fixed
> parameters and a latent class model of random parameters. However, in both
> models, there is a class in which the coefficients of some attributes and
> the constant specific alternative are very high. For example, one of the
> attributes has a coefficient of -23.1 and a standard error of 20.5; My
> quiestion esi these high coefficients could be indicating that my data are
> not adequate for these models? and I should stay with the mixed model only.
>
> Thank you
> Regards
> Elías Gordillo
>
>
> Elías José Gordillo-Chávez
> Profesor-Investigador
> División Académica de Ciencias Biológicas
> Universidad Juárez Autónoma de Tabasco
> Lab. Ecología del Paisaje y Cambio Global
>
> https://protect-au.mimecast.com/s/w9pNCWLVXkUjY2z8DS60uhC?domain=orcid.org
> Scopus Author ID: 55825273400
>
>
> _______________________________________________
> Limdep site list
> Limdep at mailman.sydney.edu.au
> https://protect-au.mimecast.com/s/r0ApCXLW2mUnN1BZOTVRHxV?domain=limdep.itls.usyd.edu.au
>
>

-- 
William Greene
Department of Economics, emeritus
Stern School of Business, New York University
44 West 4 St.
New York, NY, 10012
URL: https://protect-au.mimecast.com/s/EFWECYW8Noc3ZQkXAT93s_q?domain=people.stern.nyu.edu
Email: wgreene at stern.nyu.edu
Editor in Chief: Foundations and Trends in Econometrics
Associate Editor: Economics Letters
Associate Editor: Journal of Business and Economic Statistics