[Limdep Nlogit List] estimating wtp with a cost-income ratio in the utility function

[Arthur Caplan]

Dear Medard,

Have you thought about assigning a constrained triangular distribution to the cost coefficient? 

Arthur Caplan

-----Original Message-----
From: Limdep <limdep-bounces at mailman.sydney.edu.au> On Behalf Of medard kakuru via Limdep
Sent: Monday, October 7, 2024 6:26 AM
To: Limdep and Nlogit Mailing List <limdep at mailman.sydney.edu.au>
Cc: medard kakuru <medakseth at gmail.com>
Subject: Re: [Limdep Nlogit List] estimating wtp with a cost-income ratio in the utility function

Dear John,
Yes, my first model is to make the cost coefficient fixed and a normal distribution for other non-cost attributes. When I introduce a cost-income ratio, I give the cost coefficient a log normal. Yes, the fixed cost coefficient will not cause an explosion but it is being criticized for assuming that individuals are cost insensitive. So I try to avoid it, I make the cost coefficient log normal, which now causes an explosion.

On Mon, Oct 7, 2024 at 2:55 PM John C. Whitehead via Limdep < limdep at mailman.sydney.edu.au> wrote:

> Medard,
>
> Did you make the cost coefficient fixed (no estimated standard 
> deviation) or log normal. It is my understanding that the latter will 
> blow up your wtp estimate. In my experience a fixed cost coefficient 
> will cause no such damage.
>
> John Whitehead
>
> On Mon, Oct 7, 2024 at 7:48 AM medard kakuru via Limdep < 
> limdep at mailman.sydney.edu.au> wrote:
>
> > Dear All,
> > I am estimating mixed logit models in preference and utility spaces. 
> > My
> wtp
> > estimates are big as expected (because I made the cost parameter 
> > fixed - according to Giergizny et al., 2012). To remedy the wtp 
> > explosion, I include the cost-income ratio in the utility function, 
> > necessitating an adjustment in the usual formula of computing wtp. 
> > Please assist me with
> the
> > adjusted syntax that takes account of the ratio.
> > Thank you.
> >
> > Regards,
> >
> > Medard
> > PhD Student,
> > Makerere University Kampala
> >
> > On Thu, Oct 3, 2024 at 10:34 PM Steven Lavrenz via Limdep < 
> > limdep at mailman.sydney.edu.au> wrote:
> >
> > > Are these quantities referring to the same statistic? If so, why 
> > > the difference in naming convention within Limdep?
> > >
> > > Best Regards,
> > > Steve
> > >
> > > --
> > > Steven M. Lavrenz, PhD, RSP2I
> > > Assistant Professor
> > > Wayne State University
> > > Civil and Environmental Engineering
> > > 5050 Anthony Wayne Drive
> > > Detroit, MI 48202
> > > (313) 577-2086
> > > slavrenz at wayne.edu<mailto:slavrenz at wayne.edu>
> > >
> > >
> > > _______________________________________________
> > > Limdep site list
> > > Limdep at mailman.sydney.edu.au
> > > http://limdep.itls.usyd.edu.au
> > >
> > >
> > _______________________________________________
> > Limdep site list
> > Limdep at mailman.sydney.edu.au
> > http://limdep.itls.usyd.edu.au
> >
> _______________________________________________
> Limdep site list
> Limdep at mailman.sydney.edu.au
> http://limdep.itls.usyd.edu.au
>
_______________________________________________
Limdep site list
Limdep at mailman.sydney.edu.au
http://limdep.itls.usyd.edu.au