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

Tue Oct 8 07:50:57 AEDT 2024

I agree with Rob!

One need not always use a mixed logit, either. Latent class models can also
capture preference heterogeneity. Yet , every time I do so a referee says
that I should mixed logit because … everyone does it.

On Mon, Oct 7, 2024 at 4:42 PM Robert Johnston via Limdep <
limdep at mailman.sydney.edu.au> wrote:

> Dear Medard,
>
> I recommend that you choose a parameter distribution based on theory and
> empirical properties for your intended application, not whether you
> perceive a distribution to be commonly used in a particular area of the
> literature.
>
> Best,
>
> Robert J. Johnston
> Director, George Perkins Marsh Institute
> Professor, Department of Economics
> Chair, Clark University Institutional Review Board (IRB)
> Editor, Resource and Energy Economics
> Clark University
> 950 Main St.
> Worcester, MA 01610
> Phone: (508) 751-4619
> Email: rjohnston at clarku.edu
> Institute website: https://url.au.m.mimecastprotect.com/s/PQ4WCgZ0N1iPovv8RhNfAF46k7O?domain=clarku.edu
> IRB website:
> https://url.au.m.mimecastprotect.com/s/3L6HCjZ1N7ilBzzgXIRhWFmHLCp?domain=clarku.edu
> Google Scholar Citations:
> https://url.au.m.mimecastprotect.com/s/newhCk81N9tYKDDgjtQi9FGbR3G?domain=scholar.google.com
>
>
> -----Original Message-----
> From: Limdep <limdep-bounces at mailman.sydney.edu.au> On Behalf Of medard
> kakuru via Limdep
> Sent: Monday, October 7, 2024 4:20 PM
> To: Limdep and Nlogit Mailing List <limdep at mailman.sydney.edu.au>
> Cc: medard kakuru <medakseth at gmail.com>
> Subject: [EXT] Re: [Limdep Nlogit List] estimating wtp with a cost-income
> ratio in the utility function
>
> Dear John,
> I will try both, though prefer a log normal which is commonly used.
> Thank you.
>
> Medard
>
> On Mon, Oct 7, 2024 at 7:53 PM John C. Whitehead via Limdep <
> limdep at mailman.sydney.edu.au> wrote:
>
> > Or uniform, or normal ... any distribution on cost that is constrained
> > positive might be an improvement over a fixed cost coefficient or the
> > log functional form.
> >
> > On Mon, Oct 7, 2024 at 12:18 PM Arthur Caplan via Limdep <
> > limdep at mailman.sydney.edu.au> wrote:
> >
> > > 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
> > > > > > https://url.au.m.mimecastprotect.com/s/ZQwmClx1NjiOVWWL8HqsZFzS12N?domain=nam10.safelinks.protection.outlook.com
> > > > > > %2Flimdep.itls.usyd.edu.au%2F&data=05%7C02%7Crjohnston%40clark
> > > > > > u.edu%7C59f070913dac45bde1dc08dce70d918a%7Cb5b2263d68aa453eb97
> > > > > > 2aa1421410f80%7C0%7C0%7C638639292697640077%7CUnknown%7CTWFpbGZ
> > > > > > sb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXV
> > > > > > CI6Mn0%3D%7C0%7C%7C%7C&sdata=cfQAYpmnGu9iB%2BIxwY8IafgTJntSp91
> > > > > > Fu4VSOHrWBno%3D&reserved=0
> > > > > >
> > > > > >
> > > > > _______________________________________________
> > > > > Limdep site list
> > > > > Limdep at mailman.sydney.edu.au
> > > > > https://url.au.m.mimecastprotect.com/s/WvIsCmO5glu1gVVv3iQtGFRxL9J?domain=nam10.safelinks.protection.outlook.com
> > > > > Flimdep.itls.usyd.edu.au%2F&data=05%7C02%7Crjohnston%40clarku.ed
> > > > > u%7C59f070913dac45bde1dc08dce70d918a%7Cb5b2263d68aa453eb972aa142
> > > > > 1410f80%7C0%7C0%7C638639292697661810%7CUnknown%7CTWFpbGZsb3d8eyJ
> > > > > WIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%
> > > > > 7C0%7C%7C%7C&sdata=ahAxDVoyWN09mK%2BWNd5bjGWwQEI%2Fso6GW%2BPrSJC
> > > > > 6DDU%3D&reserved=0
> > > > >
> > > > _______________________________________________
> > > > Limdep site list
> > > > Limdep at mailman.sydney.edu.au
> > > > http://l/
> > > > imdep.itls.usyd.edu.au%2F&data=05%7C02%7Crjohnston%40clarku.edu%7C
> > > > 59f070913dac45bde1dc08dce70d918a%7Cb5b2263d68aa453eb972aa1421410f8
> > > > 0%7C0%7C0%7C638639292697678009%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4
> > > > wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C0%7C%7C%
> > > > 7C&sdata=hTgeqv1sFQEcFv0ymsLwVnHxXvpgvtjpNdzLb8NUjqo%3D&reserved=0
> > > >
> > > _______________________________________________
> > > Limdep site list
> > > Limdep at mailman.sydney.edu.au
> > > http://lim/
> > > dep.itls.usyd.edu.au%2F&data=05%7C02%7Crjohnston%40clarku.edu%7C59f0
> > > 70913dac45bde1dc08dce70d918a%7Cb5b2263d68aa453eb972aa1421410f80%7C0%
> > > 7C0%7C638639292697693757%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDA
> > > iLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C0%7C%7C%7C&sdata=K
> > > 5S%2BWeOs3I840Ty94iE0vwXqafyNt1aBtKep07jS3pE%3D&reserved=0
> > > _______________________________________________
> > > Limdep site list
> > > Limdep at mailman.sydney.edu.au
> > > http://lim/
> > > dep.itls.usyd.edu.au%2F&data=05%7C02%7Crjohnston%40clarku.edu%7C59f0
> > > 70913dac45bde1dc08dce70d918a%7Cb5b2263d68aa453eb972aa1421410f80%7C0%
> > > 7C0%7C638639292697709445%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDA
> > > iLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C0%7C%7C%7C&sdata=F
> > > caBDkaV3AK8kEGMrAVFlrS0mEuAl4cmlT7XY0ysL8k%3D&reserved=0
> > >
> > _______________________________________________
> > Limdep site list
> > Limdep at mailman.sydney.edu.au
> > http://limde/
> > p.itls.usyd.edu.au%2F&data=05%7C02%7Crjohnston%40clarku.edu%7C59f07091
> > 3dac45bde1dc08dce70d918a%7Cb5b2263d68aa453eb972aa1421410f80%7C0%7C0%7C
> > 638639292697724690%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjo
> > iV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C0%7C%7C%7C&sdata=qo2EnDz7%2F
> > LQZIsuQhcuJe7tlC8AoDVMYjFfTMgJe7Zo%3D&reserved=0
> >
> _______________________________________________
> 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
>
>