From cathy.durham at oregonstate.edu  Mon Jul  2 15:50:22 2018
From: cathy.durham at oregonstate.edu (Durham, Catherine Alison)
Date: Mon, 2 Jul 2018 05:50:22 +0000
Subject: [Limdep Nlogit List] Having trouble with the String command and
 its use in a PROC
In-Reply-To: <CAEJPMR7qC8jhvncgC=aHiQxoxu_AwxwU+O0RCWPX+LnaRnEF=A@mail.gmail.com>
References: <00E811FB06246F43A379835C171DD4D90129EA1F17@EX3.oregonstate.edu>
	<CAEJPMR7qC8jhvncgC=aHiQxoxu_AwxwU+O0RCWPX+LnaRnEF=A@mail.gmail.com>
Message-ID: <00E811FB06246F43A379835C171DD4D90129EA2769@EX3.oregonstate.edu>

Oddly, that didn't complete the fix but doing removing spaces (I think I had tabs in) as you said  and  typing 'RHS='  instead of 'Rhs=' did. 

-----Original Message-----
From: Limdep <limdep-bounces at mailman.sydney.edu.au> On Behalf Of William Greene via Limdep
Sent: Friday, June 29, 2018 5:32 PM
To: Limdep and Nlogit Mailing List <limdep at mailman.sydney.edu.au>
Cc: William Greene <wgreene at stern.nyu.edu>
Subject: Re: [Limdep Nlogit List] Having trouble with the String command and its use in a PROC

Catherine.  Remove the stray spaces after the equals sign in the STRING command.
/Bill Greene

On Fri, Jun 29, 2018 at 8:17 PM, Durham, Catherine Alison < cathy.durham at oregonstate.edu> wrote:

> Since it didn't seem to be working first I
> |-> create;c=2;y=4$ Just to give myself the same variables as in the
> example
> , I replicated the manual example:
> |-> PROC
> |-> DSTAT       ;"ST0"$
> |-> ENDPROC
> |-> STRING      ;ST0=   Rhs=c$
> |-> EXECUTE
> Error    999: The specification ; Rh is not recognized.
>
> Maximum repetitions of PROC
>
> |-> STRING      ;ST0=   Rhs=y$
> |-> EXECUTE
> Error    999: The specification ; Rh is not recognized.
>
> Maximum repetitions of PROC
> Variations in which I placed the STRING command in advance of the 
> procedure did not work either.
> In the Strings folder of the project file the ST0 don't seem to update 
> properly when I run the string command either.
>
> _______________________________________________
> Limdep site list
> Limdep at mailman.sydney.edu.au
> http://limdep.itls.usyd.edu.au
>
>


--
William Greene
Department of Economics
Stern School of Business, New York University
44 West 4 St., 7-90
New York, NY, 10012
URL: https://protect-au.mimecast.com/s/G8kFCr8DLRtN9NBrS7j0FY?domain=people.stern.nyu.edu
Email: wgreene at stern.nyu.edu
Ph. +1.212.998.0876
Editor in Chief: Journal of Productivity Analysis Editor in Chief: Foundations and Trends in Econometrics Associate Editor: Economics Letters Associate Editor: Journal of Business and Economic Statistics Associate Editor: Journal of Choice Modeling _______________________________________________
Limdep site list
Limdep at mailman.sydney.edu.au
http://limdep.itls.usyd.edu.au


From medakseth at gmail.com  Fri Jul 20 19:22:26 2018
From: medakseth at gmail.com (medard kakuru)
Date: Fri, 20 Jul 2018 12:22:26 +0300
Subject: [Limdep Nlogit List] WTp estimation
Message-ID: <CALwnpeRH25or1YDYW3JaQjT0Mz0ddiFoyoYxQpxVcgPv0JsekQ@mail.gmail.com>

Dear All,
Kindly help me with the syntax for wtp in preference space. I am running
S-MNL, G-MNL and the GMXL models and want to compare WTP estimates for the
three models. I also want to compare these estimates with those obtained
from wtp-space model estimations. I understand that for a simple MXL model,
the syntax for wtp is just a ratio of attribute and cost coefficients. Is
it the case with the models I am estimating? I expected to find the syntax
in the Nlogit manual (section N33) but it's not listed.


Secondly, I have seen the syntax for carrying out a loglikelihood ratio
test and the syntax gives the LR statistic. How do i go further to get a
p-value (say at 5%) for the statistic?

Thanks in advance.

Regards, Medard

From wgreene at stern.nyu.edu  Sun Jul 22 07:35:07 2018
From: wgreene at stern.nyu.edu (William Greene)
Date: Sat, 21 Jul 2018 17:35:07 -0400
Subject: [Limdep Nlogit List] WTp estimation
In-Reply-To: <CALwnpeRH25or1YDYW3JaQjT0Mz0ddiFoyoYxQpxVcgPv0JsekQ@mail.gmail.com>
References: <CALwnpeRH25or1YDYW3JaQjT0Mz0ddiFoyoYxQpxVcgPv0JsekQ@mail.gmail.com>
Message-ID: <CAEJPMR7JcmdByCuUsaifZDYZAb8b6POdf5p59TXzLuy9JtYmLA@mail.gmail.com>

Medard.  WTP for all variants of the RP logit model is described in
Chapter N29.  That would be good for the S-MNL and GMXL.  I'm
not sure what the G-MNL model is.  WTP is generally a ratio of
coefficients, though in RP models, the WTP is computed for each
individual.  P values for LR statistics are generally not computed.
I'm not sure what the P-value at 5% is.  You can use CALC to look
up critical values for chi-squared if you wish.  The function
CTB(prob,df) returns the critical value for probability prob with
degrees of freedom df.
Regards
/Bill Greene

On Fri, Jul 20, 2018 at 5:22 AM, medard kakuru via Limdep <
limdep at mailman.sydney.edu.au> wrote:

> Dear All,
> Kindly help me with the syntax for wtp in preference space. I am running
> S-MNL, G-MNL and the GMXL models and want to compare WTP estimates for the
> three models. I also want to compare these estimates with those obtained
> from wtp-space model estimations. I understand that for a simple MXL model,
> the syntax for wtp is just a ratio of attribute and cost coefficients. Is
> it the case with the models I am estimating? I expected to find the syntax
> in the Nlogit manual (section N33) but it's not listed.
>
>
> Secondly, I have seen the syntax for carrying out a loglikelihood ratio
> test and the syntax gives the LR statistic. How do i go further to get a
> p-value (say at 5%) for the statistic?
>
> Thanks in advance.
>
> Regards, Medard
> _______________________________________________
> Limdep site list
> Limdep at mailman.sydney.edu.au
> http://limdep.itls.usyd.edu.au
>
>


-- 
William Greene
Department of Economics
Stern School of Business, New York University
44 West 4 St., 7-90
New York, NY, 10012
URL: https://protect-au.mimecast.com/s/6czpCGvmB5ijXBZJTKS_T8?domain=people.stern.nyu.edu
Email: wgreene at stern.nyu.edu
Ph. +1.212.998.0876
Editor in Chief: Journal of Productivity Analysis
Editor in Chief: Foundations and Trends in Econometrics
Associate Editor: Economics Letters
Associate Editor: Journal of Business and Economic Statistics
Associate Editor: Journal of Choice Modeling

From medakseth at gmail.com  Tue Jul 24 23:53:24 2018
From: medakseth at gmail.com (medard kakuru)
Date: Tue, 24 Jul 2018 16:53:24 +0300
Subject: [Limdep Nlogit List] WTp estimation
In-Reply-To: <CAEJPMR7JcmdByCuUsaifZDYZAb8b6POdf5p59TXzLuy9JtYmLA@mail.gmail.com>
References: <CALwnpeRH25or1YDYW3JaQjT0Mz0ddiFoyoYxQpxVcgPv0JsekQ@mail.gmail.com>
	<CAEJPMR7JcmdByCuUsaifZDYZAb8b6POdf5p59TXzLuy9JtYmLA@mail.gmail.com>
Message-ID: <CALwnpeTUApqJds1pE0-6tjyWRX4n6zrPmJCYesToGRHXcLU9=Q@mail.gmail.com>

Thanks Bill.
I am facing another challenge. I use the wald command to estimate wtp after
estimating a mixed logit with all non-attribute coefficients given a normal
distribution and the syntax works. Since the standard deviation for one
attribute was not significant, I re-specify the model and make that
attribute non-random. Running the wald command after this specification
gives me an error message that "wrong number of start values - need one for
each label". What could be the problem?

Thanks.

Medard

On Sun, Jul 22, 2018 at 12:35 AM, William Greene via Limdep <
limdep at mailman.sydney.edu.au> wrote:

> Medard.  WTP for all variants of the RP logit model is described in
> Chapter N29.  That would be good for the S-MNL and GMXL.  I'm
> not sure what the G-MNL model is.  WTP is generally a ratio of
> coefficients, though in RP models, the WTP is computed for each
> individual.  P values for LR statistics are generally not computed.
> I'm not sure what the P-value at 5% is.  You can use CALC to look
> up critical values for chi-squared if you wish.  The function
> CTB(prob,df) returns the critical value for probability prob with
> degrees of freedom df.
> Regards
> /Bill Greene
>
> On Fri, Jul 20, 2018 at 5:22 AM, medard kakuru via Limdep <
> limdep at mailman.sydney.edu.au> wrote:
>
> > Dear All,
> > Kindly help me with the syntax for wtp in preference space. I am running
> > S-MNL, G-MNL and the GMXL models and want to compare WTP estimates for
> the
> > three models. I also want to compare these estimates with those obtained
> > from wtp-space model estimations. I understand that for a simple MXL
> model,
> > the syntax for wtp is just a ratio of attribute and cost coefficients. Is
> > it the case with the models I am estimating? I expected to find the
> syntax
> > in the Nlogit manual (section N33) but it's not listed.
> >
> >
> > Secondly, I have seen the syntax for carrying out a loglikelihood ratio
> > test and the syntax gives the LR statistic. How do i go further to get a
> > p-value (say at 5%) for the statistic?
> >
> > Thanks in advance.
> >
> > Regards, Medard
> > _______________________________________________
> > Limdep site list
> > Limdep at mailman.sydney.edu.au
> > http://limdep.itls.usyd.edu.au
> >
> >
>
>
> --
> William Greene
> Department of Economics
> Stern School of Business, New York University
> 44 West 4 St., 7-90
> New York, NY, 10012
> URL: https://protect-au.mimecast.com/s/7JqiCD1jy9tgzr49hWYuUy?domain=people.stern.nyu.edu
> Email: wgreene at stern.nyu.edu
> Ph. +1.212.998.0876
> Editor in Chief: Journal of Productivity Analysis
> Editor in Chief: Foundations and Trends in Econometrics
> Associate Editor: Economics Letters
> Associate Editor: Journal of Business and Economic Statistics
> Associate Editor: Journal of Choice Modeling
> _______________________________________________
> Limdep site list
> Limdep at mailman.sydney.edu.au
> http://limdep.itls.usyd.edu.au
>
>

From fredrik.carlsson at economics.gu.se  Wed Jul 25 00:01:31 2018
From: fredrik.carlsson at economics.gu.se (Fredrik Carlsson)
Date: Tue, 24 Jul 2018 14:01:31 +0000
Subject: [Limdep Nlogit List] WTp estimation
In-Reply-To: <CALwnpeTUApqJds1pE0-6tjyWRX4n6zrPmJCYesToGRHXcLU9=Q@mail.gmail.com>
References: <CALwnpeRH25or1YDYW3JaQjT0Mz0ddiFoyoYxQpxVcgPv0JsekQ@mail.gmail.com>
	<CAEJPMR7JcmdByCuUsaifZDYZAb8b6POdf5p59TXzLuy9JtYmLA@mail.gmail.com>,
	<CALwnpeTUApqJds1pE0-6tjyWRX4n6zrPmJCYesToGRHXcLU9=Q@mail.gmail.com>
Message-ID: <22E7A439-EAF7-43E1-B7ED-AC0731F663EC@economics.gu.se>

You have one less parameter, so reduce the number of parameters in the labels part of the Wald-command

Fredrik

Skickat fr?n min iPhone

> 24 juli 2018 kl. 15:53 skrev medard kakuru via Limdep <limdep at mailman.sydney.edu.au>:
> 
> Thanks Bill.
> I am facing another challenge. I use the wald command to estimate wtp after
> estimating a mixed logit with all non-attribute coefficients given a normal
> distribution and the syntax works. Since the standard deviation for one
> attribute was not significant, I re-specify the model and make that
> attribute non-random. Running the wald command after this specification
> gives me an error message that "wrong number of start values - need one for
> each label". What could be the problem?
> 
> Thanks.
> 
> Medard
> 
> On Sun, Jul 22, 2018 at 12:35 AM, William Greene via Limdep <
> limdep at mailman.sydney.edu.au> wrote:
> 
>> Medard.  WTP for all variants of the RP logit model is described in
>> Chapter N29.  That would be good for the S-MNL and GMXL.  I'm
>> not sure what the G-MNL model is.  WTP is generally a ratio of
>> coefficients, though in RP models, the WTP is computed for each
>> individual.  P values for LR statistics are generally not computed.
>> I'm not sure what the P-value at 5% is.  You can use CALC to look
>> up critical values for chi-squared if you wish.  The function
>> CTB(prob,df) returns the critical value for probability prob with
>> degrees of freedom df.
>> Regards
>> /Bill Greene
>> 
>> On Fri, Jul 20, 2018 at 5:22 AM, medard kakuru via Limdep <
>> limdep at mailman.sydney.edu.au> wrote:
>> 
>>> Dear All,
>>> Kindly help me with the syntax for wtp in preference space. I am running
>>> S-MNL, G-MNL and the GMXL models and want to compare WTP estimates for
>> the
>>> three models. I also want to compare these estimates with those obtained
>>> from wtp-space model estimations. I understand that for a simple MXL
>> model,
>>> the syntax for wtp is just a ratio of attribute and cost coefficients. Is
>>> it the case with the models I am estimating? I expected to find the
>> syntax
>>> in the Nlogit manual (section N33) but it's not listed.
>>> 
>>> 
>>> Secondly, I have seen the syntax for carrying out a loglikelihood ratio
>>> test and the syntax gives the LR statistic. How do i go further to get a
>>> p-value (say at 5%) for the statistic?
>>> 
>>> Thanks in advance.
>>> 
>>> Regards, Medard
>>> _______________________________________________
>>> Limdep site list
>>> Limdep at mailman.sydney.edu.au
>>> http://limdep.itls.usyd.edu.au
>>> 
>>> 
>> 
>> 
>> --
>> William Greene
>> Department of Economics
>> Stern School of Business, New York University
>> 44 West 4 St., 7-90
>> New York, NY, 10012
>> URL: https://protect-au.mimecast.com/s/dMfpCgZowLHVRgVRCNQboG?domain=people.stern.nyu.edu
>> Email: wgreene at stern.nyu.edu
>> Ph. +1.212.998.0876
>> Editor in Chief: Journal of Productivity Analysis
>> Editor in Chief: Foundations and Trends in Econometrics
>> Associate Editor: Economics Letters
>> Associate Editor: Journal of Business and Economic Statistics
>> Associate Editor: Journal of Choice Modeling
>> _______________________________________________
>> 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
> 

From wgreene at stern.nyu.edu  Wed Jul 25 00:50:41 2018
From: wgreene at stern.nyu.edu (William Greene)
Date: Tue, 24 Jul 2018 10:50:41 -0400
Subject: [Limdep Nlogit List] WTp estimation
In-Reply-To: <CALwnpeTUApqJds1pE0-6tjyWRX4n6zrPmJCYesToGRHXcLU9=Q@mail.gmail.com>
References: <CALwnpeRH25or1YDYW3JaQjT0Mz0ddiFoyoYxQpxVcgPv0JsekQ@mail.gmail.com>
	<CAEJPMR7JcmdByCuUsaifZDYZAb8b6POdf5p59TXzLuy9JtYmLA@mail.gmail.com>
	<CALwnpeTUApqJds1pE0-6tjyWRX4n6zrPmJCYesToGRHXcLU9=Q@mail.gmail.com>
Message-ID: <CAEJPMR42Qe00T8fqa=qzKX4h2WTS=pGZXE6fZ-noOvzi8DO_QQ@mail.gmail.com>

If you made the coefficient nonrandom, then you don't have the
variance term that you had in the previous specification.
/Bill Greene

On Tue, Jul 24, 2018 at 9:53 AM, medard kakuru via Limdep <
limdep at mailman.sydney.edu.au> wrote:

> Thanks Bill.
> I am facing another challenge. I use the wald command to estimate wtp after
> estimating a mixed logit with all non-attribute coefficients given a normal
> distribution and the syntax works. Since the standard deviation for one
> attribute was not significant, I re-specify the model and make that
> attribute non-random. Running the wald command after this specification
> gives me an error message that "wrong number of start values - need one for
> each label". What could be the problem?
>
> Thanks.
>
> Medard
>
> On Sun, Jul 22, 2018 at 12:35 AM, William Greene via Limdep <
> limdep at mailman.sydney.edu.au> wrote:
>
> > Medard.  WTP for all variants of the RP logit model is described in
> > Chapter N29.  That would be good for the S-MNL and GMXL.  I'm
> > not sure what the G-MNL model is.  WTP is generally a ratio of
> > coefficients, though in RP models, the WTP is computed for each
> > individual.  P values for LR statistics are generally not computed.
> > I'm not sure what the P-value at 5% is.  You can use CALC to look
> > up critical values for chi-squared if you wish.  The function
> > CTB(prob,df) returns the critical value for probability prob with
> > degrees of freedom df.
> > Regards
> > /Bill Greene
> >
> > On Fri, Jul 20, 2018 at 5:22 AM, medard kakuru via Limdep <
> > limdep at mailman.sydney.edu.au> wrote:
> >
> > > Dear All,
> > > Kindly help me with the syntax for wtp in preference space. I am
> running
> > > S-MNL, G-MNL and the GMXL models and want to compare WTP estimates for
> > the
> > > three models. I also want to compare these estimates with those
> obtained
> > > from wtp-space model estimations. I understand that for a simple MXL
> > model,
> > > the syntax for wtp is just a ratio of attribute and cost coefficients.
> Is
> > > it the case with the models I am estimating? I expected to find the
> > syntax
> > > in the Nlogit manual (section N33) but it's not listed.
> > >
> > >
> > > Secondly, I have seen the syntax for carrying out a loglikelihood ratio
> > > test and the syntax gives the LR statistic. How do i go further to get
> a
> > > p-value (say at 5%) for the statistic?
> > >
> > > Thanks in advance.
> > >
> > > Regards, Medard
> > > _______________________________________________
> > > Limdep site list
> > > Limdep at mailman.sydney.edu.au
> > > http://limdep.itls.usyd.edu.au
> > >
> > >
> >
> >
> > --
> > William Greene
> > Department of Economics
> > Stern School of Business, New York University
> > 44 West 4 St., 7-90
> > New York, NY, 10012
> > URL: https://protect-au.mimecast.com/s/z0XiCp8AJQtXWMyySPpp7C?domain=people.stern.nyu.edu
> > Email: wgreene at stern.nyu.edu
> > Ph. +1.212.998.0876
> > Editor in Chief: Journal of Productivity Analysis
> > Editor in Chief: Foundations and Trends in Econometrics
> > Associate Editor: Economics Letters
> > Associate Editor: Journal of Business and Economic Statistics
> > Associate Editor: Journal of Choice Modeling
> > _______________________________________________
> > 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
>
>


-- 
William Greene
Department of Economics
Stern School of Business, New York University
44 West 4 St., 7-90
New York, NY, 10012
URL: https://protect-au.mimecast.com/s/z0XiCp8AJQtXWMyySPpp7C?domain=people.stern.nyu.edu
Email: wgreene at stern.nyu.edu
Ph. +1.212.998.0876
Editor in Chief: Journal of Productivity Analysis
Editor in Chief: Foundations and Trends in Econometrics
Associate Editor: Economics Letters
Associate Editor: Journal of Business and Economic Statistics
Associate Editor: Journal of Choice Modeling

From wgreene at stern.nyu.edu  Wed Jul 25 00:51:14 2018
From: wgreene at stern.nyu.edu (William Greene)
Date: Tue, 24 Jul 2018 10:51:14 -0400
Subject: [Limdep Nlogit List] WTp estimation
In-Reply-To: <22E7A439-EAF7-43E1-B7ED-AC0731F663EC@economics.gu.se>
References: <CALwnpeRH25or1YDYW3JaQjT0Mz0ddiFoyoYxQpxVcgPv0JsekQ@mail.gmail.com>
	<CAEJPMR7JcmdByCuUsaifZDYZAb8b6POdf5p59TXzLuy9JtYmLA@mail.gmail.com>
	<CALwnpeTUApqJds1pE0-6tjyWRX4n6zrPmJCYesToGRHXcLU9=Q@mail.gmail.com>
	<22E7A439-EAF7-43E1-B7ED-AC0731F663EC@economics.gu.se>
Message-ID: <CAEJPMR48nFWvLa1XkgSQiC48o_-m1QOjR4NaF5RpPS=V-Qffcg@mail.gmail.com>

exactly right.  I agree
Bill Greene

On Tue, Jul 24, 2018 at 10:01 AM, Fredrik Carlsson <
fredrik.carlsson at economics.gu.se> wrote:

> You have one less parameter, so reduce the number of parameters in the
> labels part of the Wald-command
>
> Fredrik
>
> Skickat fr?n min iPhone
>
> > 24 juli 2018 kl. 15:53 skrev medard kakuru via Limdep <
> limdep at mailman.sydney.edu.au>:
> >
> > Thanks Bill.
> > I am facing another challenge. I use the wald command to estimate wtp
> after
> > estimating a mixed logit with all non-attribute coefficients given a
> normal
> > distribution and the syntax works. Since the standard deviation for one
> > attribute was not significant, I re-specify the model and make that
> > attribute non-random. Running the wald command after this specification
> > gives me an error message that "wrong number of start values - need one
> for
> > each label". What could be the problem?
> >
> > Thanks.
> >
> > Medard
> >
> > On Sun, Jul 22, 2018 at 12:35 AM, William Greene via Limdep <
> > limdep at mailman.sydney.edu.au> wrote:
> >
> >> Medard.  WTP for all variants of the RP logit model is described in
> >> Chapter N29.  That would be good for the S-MNL and GMXL.  I'm
> >> not sure what the G-MNL model is.  WTP is generally a ratio of
> >> coefficients, though in RP models, the WTP is computed for each
> >> individual.  P values for LR statistics are generally not computed.
> >> I'm not sure what the P-value at 5% is.  You can use CALC to look
> >> up critical values for chi-squared if you wish.  The function
> >> CTB(prob,df) returns the critical value for probability prob with
> >> degrees of freedom df.
> >> Regards
> >> /Bill Greene
> >>
> >> On Fri, Jul 20, 2018 at 5:22 AM, medard kakuru via Limdep <
> >> limdep at mailman.sydney.edu.au> wrote:
> >>
> >>> Dear All,
> >>> Kindly help me with the syntax for wtp in preference space. I am
> running
> >>> S-MNL, G-MNL and the GMXL models and want to compare WTP estimates for
> >> the
> >>> three models. I also want to compare these estimates with those
> obtained
> >>> from wtp-space model estimations. I understand that for a simple MXL
> >> model,
> >>> the syntax for wtp is just a ratio of attribute and cost coefficients.
> Is
> >>> it the case with the models I am estimating? I expected to find the
> >> syntax
> >>> in the Nlogit manual (section N33) but it's not listed.
> >>>
> >>>
> >>> Secondly, I have seen the syntax for carrying out a loglikelihood ratio
> >>> test and the syntax gives the LR statistic. How do i go further to get
> a
> >>> p-value (say at 5%) for the statistic?
> >>>
> >>> Thanks in advance.
> >>>
> >>> Regards, Medard
> >>> _______________________________________________
> >>> Limdep site list
> >>> Limdep at mailman.sydney.edu.au
> >>> http://limdep.itls.usyd.edu.au
> >>>
> >>>
> >>
> >>
> >> --
> >> William Greene
> >> Department of Economics
> >> Stern School of Business, New York University
> >> 44 West 4 St., 7-90
> >> New York, NY, 10012
> >> URL: https://protect-au.mimecast.com/s/Mw61CP7yOZtyRGJ8Iz-9oj?domain=people.stern.nyu.edu
> >> Email: wgreene at stern.nyu.edu
> >> Ph. +1.212.998.0876
> >> Editor in Chief: Journal of Productivity Analysis
> >> Editor in Chief: Foundations and Trends in Econometrics
> >> Associate Editor: Economics Letters
> >> Associate Editor: Journal of Business and Economic Statistics
> >> Associate Editor: Journal of Choice Modeling
> >> _______________________________________________
> >> 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
>
>


-- 
William Greene
Department of Economics
Stern School of Business, New York University
44 West 4 St., 7-90
New York, NY, 10012
URL: https://protect-au.mimecast.com/s/Mw61CP7yOZtyRGJ8Iz-9oj?domain=people.stern.nyu.edu
Email: wgreene at stern.nyu.edu
Ph. +1.212.998.0876
Editor in Chief: Journal of Productivity Analysis
Editor in Chief: Foundations and Trends in Econometrics
Associate Editor: Economics Letters
Associate Editor: Journal of Business and Economic Statistics
Associate Editor: Journal of Choice Modeling

From medakseth at gmail.com  Wed Jul 25 01:52:38 2018
From: medakseth at gmail.com (medard kakuru)
Date: Tue, 24 Jul 2018 18:52:38 +0300
Subject: [Limdep Nlogit List] WTp estimation
In-Reply-To: <CAEJPMR48nFWvLa1XkgSQiC48o_-m1QOjR4NaF5RpPS=V-Qffcg@mail.gmail.com>
References: <CALwnpeRH25or1YDYW3JaQjT0Mz0ddiFoyoYxQpxVcgPv0JsekQ@mail.gmail.com>
	<CAEJPMR7JcmdByCuUsaifZDYZAb8b6POdf5p59TXzLuy9JtYmLA@mail.gmail.com>
	<CALwnpeTUApqJds1pE0-6tjyWRX4n6zrPmJCYesToGRHXcLU9=Q@mail.gmail.com>
	<22E7A439-EAF7-43E1-B7ED-AC0731F663EC@economics.gu.se>
	<CAEJPMR48nFWvLa1XkgSQiC48o_-m1QOjR4NaF5RpPS=V-Qffcg@mail.gmail.com>
Message-ID: <CALwnpeSqDsM=Lo6EF-BN0-901p0qhZG3evA35EMNpAXhoLZtRw@mail.gmail.com>

So i can't estimate wtp using the Wald command if one of the coeffecients
is nonrandom. I also get the same error message when I apply the wald
command after estimating a gmxl in utility space. Where could I be going
wrong?

Thanks in advance.
Medard

On Tue, Jul 24, 2018, 17:51 William Greene via Limdep <
limdep at mailman.sydney.edu.au> wrote:

> exactly right.  I agree
> Bill Greene
>
> On Tue, Jul 24, 2018 at 10:01 AM, Fredrik Carlsson <
> fredrik.carlsson at economics.gu.se> wrote:
>
> > You have one less parameter, so reduce the number of parameters in the
> > labels part of the Wald-command
> >
> > Fredrik
> >
> > Skickat fr?n min iPhone
> >
> > > 24 juli 2018 kl. 15:53 skrev medard kakuru via Limdep <
> > limdep at mailman.sydney.edu.au>:
> > >
> > > Thanks Bill.
> > > I am facing another challenge. I use the wald command to estimate wtp
> > after
> > > estimating a mixed logit with all non-attribute coefficients given a
> > normal
> > > distribution and the syntax works. Since the standard deviation for one
> > > attribute was not significant, I re-specify the model and make that
> > > attribute non-random. Running the wald command after this specification
> > > gives me an error message that "wrong number of start values - need one
> > for
> > > each label". What could be the problem?
> > >
> > > Thanks.
> > >
> > > Medard
> > >
> > > On Sun, Jul 22, 2018 at 12:35 AM, William Greene via Limdep <
> > > limdep at mailman.sydney.edu.au> wrote:
> > >
> > >> Medard.  WTP for all variants of the RP logit model is described in
> > >> Chapter N29.  That would be good for the S-MNL and GMXL.  I'm
> > >> not sure what the G-MNL model is.  WTP is generally a ratio of
> > >> coefficients, though in RP models, the WTP is computed for each
> > >> individual.  P values for LR statistics are generally not computed.
> > >> I'm not sure what the P-value at 5% is.  You can use CALC to look
> > >> up critical values for chi-squared if you wish.  The function
> > >> CTB(prob,df) returns the critical value for probability prob with
> > >> degrees of freedom df.
> > >> Regards
> > >> /Bill Greene
> > >>
> > >> On Fri, Jul 20, 2018 at 5:22 AM, medard kakuru via Limdep <
> > >> limdep at mailman.sydney.edu.au> wrote:
> > >>
> > >>> Dear All,
> > >>> Kindly help me with the syntax for wtp in preference space. I am
> > running
> > >>> S-MNL, G-MNL and the GMXL models and want to compare WTP estimates
> for
> > >> the
> > >>> three models. I also want to compare these estimates with those
> > obtained
> > >>> from wtp-space model estimations. I understand that for a simple MXL
> > >> model,
> > >>> the syntax for wtp is just a ratio of attribute and cost
> coefficients.
> > Is
> > >>> it the case with the models I am estimating? I expected to find the
> > >> syntax
> > >>> in the Nlogit manual (section N33) but it's not listed.
> > >>>
> > >>>
> > >>> Secondly, I have seen the syntax for carrying out a loglikelihood
> ratio
> > >>> test and the syntax gives the LR statistic. How do i go further to
> get
> > a
> > >>> p-value (say at 5%) for the statistic?
> > >>>
> > >>> Thanks in advance.
> > >>>
> > >>> Regards, Medard
> > >>> _______________________________________________
> > >>> Limdep site list
> > >>> Limdep at mailman.sydney.edu.au
> > >>> http://limdep.itls.usyd.edu.au
> > >>>
> > >>>
> > >>
> > >>
> > >> --
> > >> William Greene
> > >> Department of Economics
> > >> Stern School of Business, New York University
> > >> 44 West 4 St., 7-90
> > >> New York, NY, 10012
> > >> URL: https://protect-au.mimecast.com/s/l30oCGvmB5ijRVjqTK1RHR?domain=people.stern.nyu.edu
> > >> Email: wgreene at stern.nyu.edu
> > >> Ph. +1.212.998.0876
> > >> Editor in Chief: Journal of Productivity Analysis
> > >> Editor in Chief: Foundations and Trends in Econometrics
> > >> Associate Editor: Economics Letters
> > >> Associate Editor: Journal of Business and Economic Statistics
> > >> Associate Editor: Journal of Choice Modeling
> > >> _______________________________________________
> > >> 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
> >
> >
>
>
> --
> William Greene
> Department of Economics
> Stern School of Business, New York University
> 44 West 4 St., 7-90
> New York, NY, 10012
> URL: https://protect-au.mimecast.com/s/l30oCGvmB5ijRVjqTK1RHR?domain=people.stern.nyu.edu
> Email: wgreene at stern.nyu.edu
> Ph. +1.212.998.0876
> Editor in Chief: Journal of Productivity Analysis
> Editor in Chief: Foundations and Trends in Econometrics
> Associate Editor: Economics Letters
> Associate Editor: Journal of Business and Economic Statistics
> Associate Editor: Journal of Choice Modeling
> _______________________________________________
> Limdep site list
> Limdep at mailman.sydney.edu.au
> http://limdep.itls.usyd.edu.au
>
>

From wgreene at stern.nyu.edu  Wed Jul 25 02:02:58 2018
From: wgreene at stern.nyu.edu (William Greene)
Date: Tue, 24 Jul 2018 12:02:58 -0400
Subject: [Limdep Nlogit List] WTp estimation
In-Reply-To: <CALwnpeSqDsM=Lo6EF-BN0-901p0qhZG3evA35EMNpAXhoLZtRw@mail.gmail.com>
References: <CALwnpeRH25or1YDYW3JaQjT0Mz0ddiFoyoYxQpxVcgPv0JsekQ@mail.gmail.com>
	<CAEJPMR7JcmdByCuUsaifZDYZAb8b6POdf5p59TXzLuy9JtYmLA@mail.gmail.com>
	<CALwnpeTUApqJds1pE0-6tjyWRX4n6zrPmJCYesToGRHXcLU9=Q@mail.gmail.com>
	<22E7A439-EAF7-43E1-B7ED-AC0731F663EC@economics.gu.se>
	<CAEJPMR48nFWvLa1XkgSQiC48o_-m1QOjR4NaF5RpPS=V-Qffcg@mail.gmail.com>
	<CALwnpeSqDsM=Lo6EF-BN0-901p0qhZG3evA35EMNpAXhoLZtRw@mail.gmail.com>
Message-ID: <CAEJPMR4jaO1gV-ua8MZZRe9-WjkwH0NsnngjgZxzx4ctfuE78w@mail.gmail.com>

Yes you can.  After estimation, double click on the B matrix and see what
is in there.
Match it up against your output.  Then submit B and VARB as the parameters
and
variance for the command.
/B. Greene

On Tue, Jul 24, 2018 at 11:52 AM, medard kakuru via Limdep <
limdep at mailman.sydney.edu.au> wrote:

> So i can't estimate wtp using the Wald command if one of the coeffecients
> is nonrandom. I also get the same error message when I apply the wald
> command after estimating a gmxl in utility space. Where could I be going
> wrong?
>
> Thanks in advance.
> Medard
>
> On Tue, Jul 24, 2018, 17:51 William Greene via Limdep <
> limdep at mailman.sydney.edu.au> wrote:
>
> > exactly right.  I agree
> > Bill Greene
> >
> > On Tue, Jul 24, 2018 at 10:01 AM, Fredrik Carlsson <
> > fredrik.carlsson at economics.gu.se> wrote:
> >
> > > You have one less parameter, so reduce the number of parameters in the
> > > labels part of the Wald-command
> > >
> > > Fredrik
> > >
> > > Skickat fr?n min iPhone
> > >
> > > > 24 juli 2018 kl. 15:53 skrev medard kakuru via Limdep <
> > > limdep at mailman.sydney.edu.au>:
> > > >
> > > > Thanks Bill.
> > > > I am facing another challenge. I use the wald command to estimate wtp
> > > after
> > > > estimating a mixed logit with all non-attribute coefficients given a
> > > normal
> > > > distribution and the syntax works. Since the standard deviation for
> one
> > > > attribute was not significant, I re-specify the model and make that
> > > > attribute non-random. Running the wald command after this
> specification
> > > > gives me an error message that "wrong number of start values - need
> one
> > > for
> > > > each label". What could be the problem?
> > > >
> > > > Thanks.
> > > >
> > > > Medard
> > > >
> > > > On Sun, Jul 22, 2018 at 12:35 AM, William Greene via Limdep <
> > > > limdep at mailman.sydney.edu.au> wrote:
> > > >
> > > >> Medard.  WTP for all variants of the RP logit model is described in
> > > >> Chapter N29.  That would be good for the S-MNL and GMXL.  I'm
> > > >> not sure what the G-MNL model is.  WTP is generally a ratio of
> > > >> coefficients, though in RP models, the WTP is computed for each
> > > >> individual.  P values for LR statistics are generally not computed.
> > > >> I'm not sure what the P-value at 5% is.  You can use CALC to look
> > > >> up critical values for chi-squared if you wish.  The function
> > > >> CTB(prob,df) returns the critical value for probability prob with
> > > >> degrees of freedom df.
> > > >> Regards
> > > >> /Bill Greene
> > > >>
> > > >> On Fri, Jul 20, 2018 at 5:22 AM, medard kakuru via Limdep <
> > > >> limdep at mailman.sydney.edu.au> wrote:
> > > >>
> > > >>> Dear All,
> > > >>> Kindly help me with the syntax for wtp in preference space. I am
> > > running
> > > >>> S-MNL, G-MNL and the GMXL models and want to compare WTP estimates
> > for
> > > >> the
> > > >>> three models. I also want to compare these estimates with those
> > > obtained
> > > >>> from wtp-space model estimations. I understand that for a simple
> MXL
> > > >> model,
> > > >>> the syntax for wtp is just a ratio of attribute and cost
> > coefficients.
> > > Is
> > > >>> it the case with the models I am estimating? I expected to find the
> > > >> syntax
> > > >>> in the Nlogit manual (section N33) but it's not listed.
> > > >>>
> > > >>>
> > > >>> Secondly, I have seen the syntax for carrying out a loglikelihood
> > ratio
> > > >>> test and the syntax gives the LR statistic. How do i go further to
> > get
> > > a
> > > >>> p-value (say at 5%) for the statistic?
> > > >>>
> > > >>> Thanks in advance.
> > > >>>
> > > >>> Regards, Medard
> > > >>> _______________________________________________
> > > >>> Limdep site list
> > > >>> Limdep at mailman.sydney.edu.au
> > > >>> http://limdep.itls.usyd.edu.au
> > > >>>
> > > >>>
> > > >>
> > > >>
> > > >> --
> > > >> William Greene
> > > >> Department of Economics
> > > >> Stern School of Business, New York University
> > > >> 44 West 4 St., 7-90
> > > >> New York, NY, 10012
> > > >> URL: https://protect-au.mimecast.com/s/RicGCGvmB5ijRVl3UKGXDa?domain=people.stern.nyu.edu
> > > >> Email: wgreene at stern.nyu.edu
> > > >> Ph. +1.212.998.0876
> > > >> Editor in Chief: Journal of Productivity Analysis
> > > >> Editor in Chief: Foundations and Trends in Econometrics
> > > >> Associate Editor: Economics Letters
> > > >> Associate Editor: Journal of Business and Economic Statistics
> > > >> Associate Editor: Journal of Choice Modeling
> > > >> _______________________________________________
> > > >> 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
> > >
> > >
> >
> >
> > --
> > William Greene
> > Department of Economics
> > Stern School of Business, New York University
> > 44 West 4 St., 7-90
> > New York, NY, 10012
> > URL: https://protect-au.mimecast.com/s/RicGCGvmB5ijRVl3UKGXDa?domain=people.stern.nyu.edu
> > Email: wgreene at stern.nyu.edu
> > Ph. +1.212.998.0876
> > Editor in Chief: Journal of Productivity Analysis
> > Editor in Chief: Foundations and Trends in Econometrics
> > Associate Editor: Economics Letters
> > Associate Editor: Journal of Business and Economic Statistics
> > Associate Editor: Journal of Choice Modeling
> > _______________________________________________
> > 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
>
>


-- 
William Greene
Department of Economics
Stern School of Business, New York University
44 West 4 St., 7-90
New York, NY, 10012
URL: https://protect-au.mimecast.com/s/RicGCGvmB5ijRVl3UKGXDa?domain=people.stern.nyu.edu
Email: wgreene at stern.nyu.edu
Ph. +1.212.998.0876
Editor in Chief: Journal of Productivity Analysis
Editor in Chief: Foundations and Trends in Econometrics
Associate Editor: Economics Letters
Associate Editor: Journal of Business and Economic Statistics
Associate Editor: Journal of Choice Modeling

From medakseth at gmail.com  Wed Jul 25 02:34:55 2018
From: medakseth at gmail.com (medard kakuru)
Date: Tue, 24 Jul 2018 19:34:55 +0300
Subject: [Limdep Nlogit List] WTp estimation
In-Reply-To: <CAEJPMR4jaO1gV-ua8MZZRe9-WjkwH0NsnngjgZxzx4ctfuE78w@mail.gmail.com>
References: <CALwnpeRH25or1YDYW3JaQjT0Mz0ddiFoyoYxQpxVcgPv0JsekQ@mail.gmail.com>
	<CAEJPMR7JcmdByCuUsaifZDYZAb8b6POdf5p59TXzLuy9JtYmLA@mail.gmail.com>
	<CALwnpeTUApqJds1pE0-6tjyWRX4n6zrPmJCYesToGRHXcLU9=Q@mail.gmail.com>
	<22E7A439-EAF7-43E1-B7ED-AC0731F663EC@economics.gu.se>
	<CAEJPMR48nFWvLa1XkgSQiC48o_-m1QOjR4NaF5RpPS=V-Qffcg@mail.gmail.com>
	<CALwnpeSqDsM=Lo6EF-BN0-901p0qhZG3evA35EMNpAXhoLZtRw@mail.gmail.com>
	<CAEJPMR4jaO1gV-ua8MZZRe9-WjkwH0NsnngjgZxzx4ctfuE78w@mail.gmail.com>
Message-ID: <CALwnpeQs5+DoyTHY4bxEWbN3rr0FU+whqr9WvT4mHfo4u+tgaQ@mail.gmail.com>

Thanks Bill.
However, I seem not to understand the matching and the submission you are
talking about. Kindly give me a reference in the nlogit manual so that I
read for more understanding.
Thanks.
Medard
On Tue, Jul 24, 2018, 19:03 William Greene via Limdep <
limdep at mailman.sydney.edu.au> wrote:

> Yes you can.  After estimation, double click on the B matrix and see what
> is in there.
> Match it up against your output.  Then submit B and VARB as the parameters
> and
> variance for the command.
> /B. Greene
>
> On Tue, Jul 24, 2018 at 11:52 AM, medard kakuru via Limdep <
> limdep at mailman.sydney.edu.au> wrote:
>
> > So i can't estimate wtp using the Wald command if one of the coeffecients
> > is nonrandom. I also get the same error message when I apply the wald
> > command after estimating a gmxl in utility space. Where could I be going
> > wrong?
> >
> > Thanks in advance.
> > Medard
> >
> > On Tue, Jul 24, 2018, 17:51 William Greene via Limdep <
> > limdep at mailman.sydney.edu.au> wrote:
> >
> > > exactly right.  I agree
> > > Bill Greene
> > >
> > > On Tue, Jul 24, 2018 at 10:01 AM, Fredrik Carlsson <
> > > fredrik.carlsson at economics.gu.se> wrote:
> > >
> > > > You have one less parameter, so reduce the number of parameters in
> the
> > > > labels part of the Wald-command
> > > >
> > > > Fredrik
> > > >
> > > > Skickat fr?n min iPhone
> > > >
> > > > > 24 juli 2018 kl. 15:53 skrev medard kakuru via Limdep <
> > > > limdep at mailman.sydney.edu.au>:
> > > > >
> > > > > Thanks Bill.
> > > > > I am facing another challenge. I use the wald command to estimate
> wtp
> > > > after
> > > > > estimating a mixed logit with all non-attribute coefficients given
> a
> > > > normal
> > > > > distribution and the syntax works. Since the standard deviation for
> > one
> > > > > attribute was not significant, I re-specify the model and make that
> > > > > attribute non-random. Running the wald command after this
> > specification
> > > > > gives me an error message that "wrong number of start values - need
> > one
> > > > for
> > > > > each label". What could be the problem?
> > > > >
> > > > > Thanks.
> > > > >
> > > > > Medard
> > > > >
> > > > > On Sun, Jul 22, 2018 at 12:35 AM, William Greene via Limdep <
> > > > > limdep at mailman.sydney.edu.au> wrote:
> > > > >
> > > > >> Medard.  WTP for all variants of the RP logit model is described
> in
> > > > >> Chapter N29.  That would be good for the S-MNL and GMXL.  I'm
> > > > >> not sure what the G-MNL model is.  WTP is generally a ratio of
> > > > >> coefficients, though in RP models, the WTP is computed for each
> > > > >> individual.  P values for LR statistics are generally not
> computed.
> > > > >> I'm not sure what the P-value at 5% is.  You can use CALC to look
> > > > >> up critical values for chi-squared if you wish.  The function
> > > > >> CTB(prob,df) returns the critical value for probability prob with
> > > > >> degrees of freedom df.
> > > > >> Regards
> > > > >> /Bill Greene
> > > > >>
> > > > >> On Fri, Jul 20, 2018 at 5:22 AM, medard kakuru via Limdep <
> > > > >> limdep at mailman.sydney.edu.au> wrote:
> > > > >>
> > > > >>> Dear All,
> > > > >>> Kindly help me with the syntax for wtp in preference space. I am
> > > > running
> > > > >>> S-MNL, G-MNL and the GMXL models and want to compare WTP
> estimates
> > > for
> > > > >> the
> > > > >>> three models. I also want to compare these estimates with those
> > > > obtained
> > > > >>> from wtp-space model estimations. I understand that for a simple
> > MXL
> > > > >> model,
> > > > >>> the syntax for wtp is just a ratio of attribute and cost
> > > coefficients.
> > > > Is
> > > > >>> it the case with the models I am estimating? I expected to find
> the
> > > > >> syntax
> > > > >>> in the Nlogit manual (section N33) but it's not listed.
> > > > >>>
> > > > >>>
> > > > >>> Secondly, I have seen the syntax for carrying out a loglikelihood
> > > ratio
> > > > >>> test and the syntax gives the LR statistic. How do i go further
> to
> > > get
> > > > a
> > > > >>> p-value (say at 5%) for the statistic?
> > > > >>>
> > > > >>> Thanks in advance.
> > > > >>>
> > > > >>> Regards, Medard
> > > > >>> _______________________________________________
> > > > >>> Limdep site list
> > > > >>> Limdep at mailman.sydney.edu.au
> > > > >>> http://limdep.itls.usyd.edu.au
> > > > >>>
> > > > >>>
> > > > >>
> > > > >>
> > > > >> --
> > > > >> William Greene
> > > > >> Department of Economics
> > > > >> Stern School of Business, New York University
> > > > >> 44 West 4 St., 7-90
> > > > >> New York, NY, 10012
> > > > >> URL: https://protect-au.mimecast.com/s/oGUAClxwB5Cg8jQNiGQVT8?domain=people.stern.nyu.edu
> > > > >> Email: wgreene at stern.nyu.edu
> > > > >> Ph. +1.212.998.0876
> > > > >> Editor in Chief: Journal of Productivity Analysis
> > > > >> Editor in Chief: Foundations and Trends in Econometrics
> > > > >> Associate Editor: Economics Letters
> > > > >> Associate Editor: Journal of Business and Economic Statistics
> > > > >> Associate Editor: Journal of Choice Modeling
> > > > >> _______________________________________________
> > > > >> 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
> > > >
> > > >
> > >
> > >
> > > --
> > > William Greene
> > > Department of Economics
> > > Stern School of Business, New York University
> > > 44 West 4 St., 7-90
> > > New York, NY, 10012
> > > URL: https://protect-au.mimecast.com/s/oGUAClxwB5Cg8jQNiGQVT8?domain=people.stern.nyu.edu
> > > Email: wgreene at stern.nyu.edu
> > > Ph. +1.212.998.0876
> > > Editor in Chief: Journal of Productivity Analysis
> > > Editor in Chief: Foundations and Trends in Econometrics
> > > Associate Editor: Economics Letters
> > > Associate Editor: Journal of Business and Economic Statistics
> > > Associate Editor: Journal of Choice Modeling
> > > _______________________________________________
> > > 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
> >
> >
>
>
> --
> William Greene
> Department of Economics
> Stern School of Business, New York University
> 44 West 4 St., 7-90
> New York, NY, 10012
> URL: https://protect-au.mimecast.com/s/oGUAClxwB5Cg8jQNiGQVT8?domain=people.stern.nyu.edu
> Email: wgreene at stern.nyu.edu
> Ph. +1.212.998.0876
> Editor in Chief: Journal of Productivity Analysis
> Editor in Chief: Foundations and Trends in Econometrics
> Associate Editor: Economics Letters
> Associate Editor: Journal of Business and Economic Statistics
> Associate Editor: Journal of Choice Modeling
> _______________________________________________
> Limdep site list
> Limdep at mailman.sydney.edu.au
> http://limdep.itls.usyd.edu.au
>
>

From wgreene at stern.nyu.edu  Wed Jul 25 03:42:07 2018
From: wgreene at stern.nyu.edu (William Greene)
Date: Tue, 24 Jul 2018 13:42:07 -0400
Subject: [Limdep Nlogit List] WTp estimation
In-Reply-To: <CALwnpeQs5+DoyTHY4bxEWbN3rr0FU+whqr9WvT4mHfo4u+tgaQ@mail.gmail.com>
References: <CALwnpeRH25or1YDYW3JaQjT0Mz0ddiFoyoYxQpxVcgPv0JsekQ@mail.gmail.com>
	<CAEJPMR7JcmdByCuUsaifZDYZAb8b6POdf5p59TXzLuy9JtYmLA@mail.gmail.com>
	<CALwnpeTUApqJds1pE0-6tjyWRX4n6zrPmJCYesToGRHXcLU9=Q@mail.gmail.com>
	<22E7A439-EAF7-43E1-B7ED-AC0731F663EC@economics.gu.se>
	<CAEJPMR48nFWvLa1XkgSQiC48o_-m1QOjR4NaF5RpPS=V-Qffcg@mail.gmail.com>
	<CALwnpeSqDsM=Lo6EF-BN0-901p0qhZG3evA35EMNpAXhoLZtRw@mail.gmail.com>
	<CAEJPMR4jaO1gV-ua8MZZRe9-WjkwH0NsnngjgZxzx4ctfuE78w@mail.gmail.com>
	<CALwnpeQs5+DoyTHY4bxEWbN3rr0FU+whqr9WvT4mHfo4u+tgaQ@mail.gmail.com>
Message-ID: <CAEJPMR6=szZ_rNuGVyTxmaJCoke6idN9=S9dzKgmU3QapaJ5dg@mail.gmail.com>

Medard.  Look at your output in the output window.  Then, double click B in
the
project window, and you will see what is contained in B in the right
order.  When
you use ;Start=B ; Var = Varb you can then use the right ;Labels = list...
THEN
set up your functions.
/.B. Greene

On Tue, Jul 24, 2018 at 12:34 PM, medard kakuru via Limdep <
limdep at mailman.sydney.edu.au> wrote:

> Thanks Bill.
> However, I seem not to understand the matching and the submission you are
> talking about. Kindly give me a reference in the nlogit manual so that I
> read for more understanding.
> Thanks.
> Medard
> On Tue, Jul 24, 2018, 19:03 William Greene via Limdep <
> limdep at mailman.sydney.edu.au> wrote:
>
> > Yes you can.  After estimation, double click on the B matrix and see what
> > is in there.
> > Match it up against your output.  Then submit B and VARB as the
> parameters
> > and
> > variance for the command.
> > /B. Greene
> >
> > On Tue, Jul 24, 2018 at 11:52 AM, medard kakuru via Limdep <
> > limdep at mailman.sydney.edu.au> wrote:
> >
> > > So i can't estimate wtp using the Wald command if one of the
> coeffecients
> > > is nonrandom. I also get the same error message when I apply the wald
> > > command after estimating a gmxl in utility space. Where could I be
> going
> > > wrong?
> > >
> > > Thanks in advance.
> > > Medard
> > >
> > > On Tue, Jul 24, 2018, 17:51 William Greene via Limdep <
> > > limdep at mailman.sydney.edu.au> wrote:
> > >
> > > > exactly right.  I agree
> > > > Bill Greene
> > > >
> > > > On Tue, Jul 24, 2018 at 10:01 AM, Fredrik Carlsson <
> > > > fredrik.carlsson at economics.gu.se> wrote:
> > > >
> > > > > You have one less parameter, so reduce the number of parameters in
> > the
> > > > > labels part of the Wald-command
> > > > >
> > > > > Fredrik
> > > > >
> > > > > Skickat fr?n min iPhone
> > > > >
> > > > > > 24 juli 2018 kl. 15:53 skrev medard kakuru via Limdep <
> > > > > limdep at mailman.sydney.edu.au>:
> > > > > >
> > > > > > Thanks Bill.
> > > > > > I am facing another challenge. I use the wald command to estimate
> > wtp
> > > > > after
> > > > > > estimating a mixed logit with all non-attribute coefficients
> given
> > a
> > > > > normal
> > > > > > distribution and the syntax works. Since the standard deviation
> for
> > > one
> > > > > > attribute was not significant, I re-specify the model and make
> that
> > > > > > attribute non-random. Running the wald command after this
> > > specification
> > > > > > gives me an error message that "wrong number of start values -
> need
> > > one
> > > > > for
> > > > > > each label". What could be the problem?
> > > > > >
> > > > > > Thanks.
> > > > > >
> > > > > > Medard
> > > > > >
> > > > > > On Sun, Jul 22, 2018 at 12:35 AM, William Greene via Limdep <
> > > > > > limdep at mailman.sydney.edu.au> wrote:
> > > > > >
> > > > > >> Medard.  WTP for all variants of the RP logit model is described
> > in
> > > > > >> Chapter N29.  That would be good for the S-MNL and GMXL.  I'm
> > > > > >> not sure what the G-MNL model is.  WTP is generally a ratio of
> > > > > >> coefficients, though in RP models, the WTP is computed for each
> > > > > >> individual.  P values for LR statistics are generally not
> > computed.
> > > > > >> I'm not sure what the P-value at 5% is.  You can use CALC to
> look
> > > > > >> up critical values for chi-squared if you wish.  The function
> > > > > >> CTB(prob,df) returns the critical value for probability prob
> with
> > > > > >> degrees of freedom df.
> > > > > >> Regards
> > > > > >> /Bill Greene
> > > > > >>
> > > > > >> On Fri, Jul 20, 2018 at 5:22 AM, medard kakuru via Limdep <
> > > > > >> limdep at mailman.sydney.edu.au> wrote:
> > > > > >>
> > > > > >>> Dear All,
> > > > > >>> Kindly help me with the syntax for wtp in preference space. I
> am
> > > > > running
> > > > > >>> S-MNL, G-MNL and the GMXL models and want to compare WTP
> > estimates
> > > > for
> > > > > >> the
> > > > > >>> three models. I also want to compare these estimates with those
> > > > > obtained
> > > > > >>> from wtp-space model estimations. I understand that for a
> simple
> > > MXL
> > > > > >> model,
> > > > > >>> the syntax for wtp is just a ratio of attribute and cost
> > > > coefficients.
> > > > > Is
> > > > > >>> it the case with the models I am estimating? I expected to find
> > the
> > > > > >> syntax
> > > > > >>> in the Nlogit manual (section N33) but it's not listed.
> > > > > >>>
> > > > > >>>
> > > > > >>> Secondly, I have seen the syntax for carrying out a
> loglikelihood
> > > > ratio
> > > > > >>> test and the syntax gives the LR statistic. How do i go further
> > to
> > > > get
> > > > > a
> > > > > >>> p-value (say at 5%) for the statistic?
> > > > > >>>
> > > > > >>> Thanks in advance.
> > > > > >>>
> > > > > >>> Regards, Medard
> > > > > >>> _______________________________________________
> > > > > >>> Limdep site list
> > > > > >>> Limdep at mailman.sydney.edu.au
> > > > > >>> http://limdep.itls.usyd.edu.au
> > > > > >>>
> > > > > >>>
> > > > > >>
> > > > > >>
> > > > > >> --
> > > > > >> William Greene
> > > > > >> Department of Economics
> > > > > >> Stern School of Business, New York University
> > > > > >> 44 West 4 St., 7-90
> > > > > >> New York, NY, 10012
> > > > > >> URL: https://protect-au.mimecast.com/s/4mfKCK1qJZt3N7ZrfMr_rF?domain=people.stern.nyu.edu
> > > > > >> Email: wgreene at stern.nyu.edu
> > > > > >> Ph. +1.212.998.0876
> > > > > >> Editor in Chief: Journal of Productivity Analysis
> > > > > >> Editor in Chief: Foundations and Trends in Econometrics
> > > > > >> Associate Editor: Economics Letters
> > > > > >> Associate Editor: Journal of Business and Economic Statistics
> > > > > >> Associate Editor: Journal of Choice Modeling
> > > > > >> _______________________________________________
> > > > > >> 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
> > > > >
> > > > >
> > > >
> > > >
> > > > --
> > > > William Greene
> > > > Department of Economics
> > > > Stern School of Business, New York University
> > > > 44 West 4 St., 7-90
> > > > New York, NY, 10012
> > > > URL: https://protect-au.mimecast.com/s/4mfKCK1qJZt3N7ZrfMr_rF?domain=people.stern.nyu.edu
> > > > Email: wgreene at stern.nyu.edu
> > > > Ph. +1.212.998.0876
> > > > Editor in Chief: Journal of Productivity Analysis
> > > > Editor in Chief: Foundations and Trends in Econometrics
> > > > Associate Editor: Economics Letters
> > > > Associate Editor: Journal of Business and Economic Statistics
> > > > Associate Editor: Journal of Choice Modeling
> > > > _______________________________________________
> > > > 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
> > >
> > >
> >
> >
> > --
> > William Greene
> > Department of Economics
> > Stern School of Business, New York University
> > 44 West 4 St., 7-90
> > New York, NY, 10012
> > URL: https://protect-au.mimecast.com/s/4mfKCK1qJZt3N7ZrfMr_rF?domain=people.stern.nyu.edu
> > Email: wgreene at stern.nyu.edu
> > Ph. +1.212.998.0876
> > Editor in Chief: Journal of Productivity Analysis
> > Editor in Chief: Foundations and Trends in Econometrics
> > Associate Editor: Economics Letters
> > Associate Editor: Journal of Business and Economic Statistics
> > Associate Editor: Journal of Choice Modeling
> > _______________________________________________
> > 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
>
>


-- 
William Greene
Department of Economics
Stern School of Business, New York University
44 West 4 St., 7-90
New York, NY, 10012
URL: https://protect-au.mimecast.com/s/4mfKCK1qJZt3N7ZrfMr_rF?domain=people.stern.nyu.edu
Email: wgreene at stern.nyu.edu
Ph. +1.212.998.0876
Editor in Chief: Journal of Productivity Analysis
Editor in Chief: Foundations and Trends in Econometrics
Associate Editor: Economics Letters
Associate Editor: Journal of Business and Economic Statistics
Associate Editor: Journal of Choice Modeling

From medakseth at gmail.com  Wed Jul 25 03:56:24 2018
From: medakseth at gmail.com (medard kakuru)
Date: Tue, 24 Jul 2018 20:56:24 +0300
Subject: [Limdep Nlogit List] WTp estimation
In-Reply-To: <CAEJPMR6=szZ_rNuGVyTxmaJCoke6idN9=S9dzKgmU3QapaJ5dg@mail.gmail.com>
References: <CALwnpeRH25or1YDYW3JaQjT0Mz0ddiFoyoYxQpxVcgPv0JsekQ@mail.gmail.com>
	<CAEJPMR7JcmdByCuUsaifZDYZAb8b6POdf5p59TXzLuy9JtYmLA@mail.gmail.com>
	<CALwnpeTUApqJds1pE0-6tjyWRX4n6zrPmJCYesToGRHXcLU9=Q@mail.gmail.com>
	<22E7A439-EAF7-43E1-B7ED-AC0731F663EC@economics.gu.se>
	<CAEJPMR48nFWvLa1XkgSQiC48o_-m1QOjR4NaF5RpPS=V-Qffcg@mail.gmail.com>
	<CALwnpeSqDsM=Lo6EF-BN0-901p0qhZG3evA35EMNpAXhoLZtRw@mail.gmail.com>
	<CAEJPMR4jaO1gV-ua8MZZRe9-WjkwH0NsnngjgZxzx4ctfuE78w@mail.gmail.com>
	<CALwnpeQs5+DoyTHY4bxEWbN3rr0FU+whqr9WvT4mHfo4u+tgaQ@mail.gmail.com>
	<CAEJPMR6=szZ_rNuGVyTxmaJCoke6idN9=S9dzKgmU3QapaJ5dg@mail.gmail.com>
Message-ID: <CALwnpeR+N3e1FON0XX+zXKOHMARHTzWXgNRXH_eOHMKeknx62w@mail.gmail.com>

Dear Bill,
Precisely, this is what I am doing.

WALD; Labels=colb,
            colw,
            colc,
            tast,
            tex,
            smel,
            siz,
            pric,
            SD_colb,
            SD_colw,
            SD_colc,
            SD_tast,
            SD_tex,
            SD_siz,
            SD_smel,
            SD_pric
            ;start=b
            ;Var=Varb
            ;Fn1=-1*(colb/pric)
            ;Fn2=-1*(colw/pric)
            ;Fn3=-1*(colc/pric)
            ;Fn4=-1*(tast/pric)
            ;Fn5=-1*(tex/pric)
            ;Fn6=-1*(siz/pric)
            ;Fn7=-1*(smel/pric)$


When I double click the B matrix, I see one column with 15 entries in it.
How am  I supposed to use the entries in the specification above, since I
have arleady specified b as starting values?

Thanks,

Medard



On Tue, Jul 24, 2018 at 8:42 PM, William Greene via Limdep <
limdep at mailman.sydney.edu.au> wrote:

> Medard.  Look at your output in the output window.  Then, double click B in
> the
> project window, and you will see what is contained in B in the right
> order.  When
> you use ;Start=B ; Var = Varb you can then use the right ;Labels = list...
> THEN
> set up your functions.
> /.B. Greene
>
> On Tue, Jul 24, 2018 at 12:34 PM, medard kakuru via Limdep <
> limdep at mailman.sydney.edu.au> wrote:
>
> > Thanks Bill.
> > However, I seem not to understand the matching and the submission you are
> > talking about. Kindly give me a reference in the nlogit manual so that I
> > read for more understanding.
> > Thanks.
> > Medard
> > On Tue, Jul 24, 2018, 19:03 William Greene via Limdep <
> > limdep at mailman.sydney.edu.au> wrote:
> >
> > > Yes you can.  After estimation, double click on the B matrix and see
> what
> > > is in there.
> > > Match it up against your output.  Then submit B and VARB as the
> > parameters
> > > and
> > > variance for the command.
> > > /B. Greene
> > >
> > > On Tue, Jul 24, 2018 at 11:52 AM, medard kakuru via Limdep <
> > > limdep at mailman.sydney.edu.au> wrote:
> > >
> > > > So i can't estimate wtp using the Wald command if one of the
> > coeffecients
> > > > is nonrandom. I also get the same error message when I apply the wald
> > > > command after estimating a gmxl in utility space. Where could I be
> > going
> > > > wrong?
> > > >
> > > > Thanks in advance.
> > > > Medard
> > > >
> > > > On Tue, Jul 24, 2018, 17:51 William Greene via Limdep <
> > > > limdep at mailman.sydney.edu.au> wrote:
> > > >
> > > > > exactly right.  I agree
> > > > > Bill Greene
> > > > >
> > > > > On Tue, Jul 24, 2018 at 10:01 AM, Fredrik Carlsson <
> > > > > fredrik.carlsson at economics.gu.se> wrote:
> > > > >
> > > > > > You have one less parameter, so reduce the number of parameters
> in
> > > the
> > > > > > labels part of the Wald-command
> > > > > >
> > > > > > Fredrik
> > > > > >
> > > > > > Skickat fr?n min iPhone
> > > > > >
> > > > > > > 24 juli 2018 kl. 15:53 skrev medard kakuru via Limdep <
> > > > > > limdep at mailman.sydney.edu.au>:
> > > > > > >
> > > > > > > Thanks Bill.
> > > > > > > I am facing another challenge. I use the wald command to
> estimate
> > > wtp
> > > > > > after
> > > > > > > estimating a mixed logit with all non-attribute coefficients
> > given
> > > a
> > > > > > normal
> > > > > > > distribution and the syntax works. Since the standard deviation
> > for
> > > > one
> > > > > > > attribute was not significant, I re-specify the model and make
> > that
> > > > > > > attribute non-random. Running the wald command after this
> > > > specification
> > > > > > > gives me an error message that "wrong number of start values -
> > need
> > > > one
> > > > > > for
> > > > > > > each label". What could be the problem?
> > > > > > >
> > > > > > > Thanks.
> > > > > > >
> > > > > > > Medard
> > > > > > >
> > > > > > > On Sun, Jul 22, 2018 at 12:35 AM, William Greene via Limdep <
> > > > > > > limdep at mailman.sydney.edu.au> wrote:
> > > > > > >
> > > > > > >> Medard.  WTP for all variants of the RP logit model is
> described
> > > in
> > > > > > >> Chapter N29.  That would be good for the S-MNL and GMXL.  I'm
> > > > > > >> not sure what the G-MNL model is.  WTP is generally a ratio of
> > > > > > >> coefficients, though in RP models, the WTP is computed for
> each
> > > > > > >> individual.  P values for LR statistics are generally not
> > > computed.
> > > > > > >> I'm not sure what the P-value at 5% is.  You can use CALC to
> > look
> > > > > > >> up critical values for chi-squared if you wish.  The function
> > > > > > >> CTB(prob,df) returns the critical value for probability prob
> > with
> > > > > > >> degrees of freedom df.
> > > > > > >> Regards
> > > > > > >> /Bill Greene
> > > > > > >>
> > > > > > >> On Fri, Jul 20, 2018 at 5:22 AM, medard kakuru via Limdep <
> > > > > > >> limdep at mailman.sydney.edu.au> wrote:
> > > > > > >>
> > > > > > >>> Dear All,
> > > > > > >>> Kindly help me with the syntax for wtp in preference space. I
> > am
> > > > > > running
> > > > > > >>> S-MNL, G-MNL and the GMXL models and want to compare WTP
> > > estimates
> > > > > for
> > > > > > >> the
> > > > > > >>> three models. I also want to compare these estimates with
> those
> > > > > > obtained
> > > > > > >>> from wtp-space model estimations. I understand that for a
> > simple
> > > > MXL
> > > > > > >> model,
> > > > > > >>> the syntax for wtp is just a ratio of attribute and cost
> > > > > coefficients.
> > > > > > Is
> > > > > > >>> it the case with the models I am estimating? I expected to
> find
> > > the
> > > > > > >> syntax
> > > > > > >>> in the Nlogit manual (section N33) but it's not listed.
> > > > > > >>>
> > > > > > >>>
> > > > > > >>> Secondly, I have seen the syntax for carrying out a
> > loglikelihood
> > > > > ratio
> > > > > > >>> test and the syntax gives the LR statistic. How do i go
> further
> > > to
> > > > > get
> > > > > > a
> > > > > > >>> p-value (say at 5%) for the statistic?
> > > > > > >>>
> > > > > > >>> Thanks in advance.
> > > > > > >>>
> > > > > > >>> Regards, Medard
> > > > > > >>> _______________________________________________
> > > > > > >>> Limdep site list
> > > > > > >>> Limdep at mailman.sydney.edu.au
> > > > > > >>> http://limdep.itls.usyd.edu.au
> > > > > > >>>
> > > > > > >>>
> > > > > > >>
> > > > > > >>
> > > > > > >> --
> > > > > > >> William Greene
> > > > > > >> Department of Economics
> > > > > > >> Stern School of Business, New York University
> > > > > > >> 44 West 4 St., 7-90
> > > > > > >> New York, NY, 10012
> > > > > > >> URL: https://protect-au.mimecast.com/s/93YJCnxyErCM291qI9T44P?domain=people.stern.nyu.edu
> > > > > > >> Email: wgreene at stern.nyu.edu
> > > > > > >> Ph. +1.212.998.0876
> > > > > > >> Editor in Chief: Journal of Productivity Analysis
> > > > > > >> Editor in Chief: Foundations and Trends in Econometrics
> > > > > > >> Associate Editor: Economics Letters
> > > > > > >> Associate Editor: Journal of Business and Economic Statistics
> > > > > > >> Associate Editor: Journal of Choice Modeling
> > > > > > >> _______________________________________________
> > > > > > >> 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
> > > > > >
> > > > > >
> > > > >
> > > > >
> > > > > --
> > > > > William Greene
> > > > > Department of Economics
> > > > > Stern School of Business, New York University
> > > > > 44 West 4 St., 7-90
> > > > > New York, NY, 10012
> > > > > URL: https://protect-au.mimecast.com/s/93YJCnxyErCM291qI9T44P?domain=people.stern.nyu.edu
> > > > > Email: wgreene at stern.nyu.edu
> > > > > Ph. +1.212.998.0876
> > > > > Editor in Chief: Journal of Productivity Analysis
> > > > > Editor in Chief: Foundations and Trends in Econometrics
> > > > > Associate Editor: Economics Letters
> > > > > Associate Editor: Journal of Business and Economic Statistics
> > > > > Associate Editor: Journal of Choice Modeling
> > > > > _______________________________________________
> > > > > 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
> > > >
> > > >
> > >
> > >
> > > --
> > > William Greene
> > > Department of Economics
> > > Stern School of Business, New York University
> > > 44 West 4 St., 7-90
> > > New York, NY, 10012
> > > URL: https://protect-au.mimecast.com/s/93YJCnxyErCM291qI9T44P?domain=people.stern.nyu.edu
> > > Email: wgreene at stern.nyu.edu
> > > Ph. +1.212.998.0876
> > > Editor in Chief: Journal of Productivity Analysis
> > > Editor in Chief: Foundations and Trends in Econometrics
> > > Associate Editor: Economics Letters
> > > Associate Editor: Journal of Business and Economic Statistics
> > > Associate Editor: Journal of Choice Modeling
> > > _______________________________________________
> > > 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
> >
> >
>
>
> --
> William Greene
> Department of Economics
> Stern School of Business, New York University
> 44 West 4 St., 7-90
> New York, NY, 10012
> URL: https://protect-au.mimecast.com/s/93YJCnxyErCM291qI9T44P?domain=people.stern.nyu.edu
> Email: wgreene at stern.nyu.edu
> Ph. +1.212.998.0876
> Editor in Chief: Journal of Productivity Analysis
> Editor in Chief: Foundations and Trends in Econometrics
> Associate Editor: Economics Letters
> Associate Editor: Journal of Business and Economic Statistics
> Associate Editor: Journal of Choice Modeling
> _______________________________________________
> Limdep site list
> Limdep at mailman.sydney.edu.au
> http://limdep.itls.usyd.edu.au
>
>

From fredrik.carlsson at economics.gu.se  Wed Jul 25 04:03:15 2018
From: fredrik.carlsson at economics.gu.se (Fredrik Carlsson)
Date: Tue, 24 Jul 2018 18:03:15 +0000
Subject: [Limdep Nlogit List] WTp estimation
In-Reply-To: <CALwnpeR+N3e1FON0XX+zXKOHMARHTzWXgNRXH_eOHMKeknx62w@mail.gmail.com>
References: <CALwnpeRH25or1YDYW3JaQjT0Mz0ddiFoyoYxQpxVcgPv0JsekQ@mail.gmail.com>
	<CAEJPMR7JcmdByCuUsaifZDYZAb8b6POdf5p59TXzLuy9JtYmLA@mail.gmail.com>
	<CALwnpeTUApqJds1pE0-6tjyWRX4n6zrPmJCYesToGRHXcLU9=Q@mail.gmail.com>
	<22E7A439-EAF7-43E1-B7ED-AC0731F663EC@economics.gu.se>
	<CAEJPMR48nFWvLa1XkgSQiC48o_-m1QOjR4NaF5RpPS=V-Qffcg@mail.gmail.com>
	<CALwnpeSqDsM=Lo6EF-BN0-901p0qhZG3evA35EMNpAXhoLZtRw@mail.gmail.com>
	<CAEJPMR4jaO1gV-ua8MZZRe9-WjkwH0NsnngjgZxzx4ctfuE78w@mail.gmail.com>
	<CALwnpeQs5+DoyTHY4bxEWbN3rr0FU+whqr9WvT4mHfo4u+tgaQ@mail.gmail.com>
	<CAEJPMR6=szZ_rNuGVyTxmaJCoke6idN9=S9dzKgmU3QapaJ5dg@mail.gmail.com>,
	<CALwnpeR+N3e1FON0XX+zXKOHMARHTzWXgNRXH_eOHMKeknx62w@mail.gmail.com>
Message-ID: <A00AD1FA-9151-4EC0-8B03-7479D7F73D44@economics.gu.se>

You should most likely take away SD_pric from labels. I assume this was the label for the random price coefficient that is now fixed instead 

Fredrik

Skickat fr?n min iPhone

> 24 juli 2018 kl. 19:56 skrev medard kakuru via Limdep <limdep at mailman.sydney.edu.au>:
> 
> Dear Bill,
> Precisely, this is what I am doing.
> 
> WALD; Labels=colb,
>            colw,
>            colc,
>            tast,
>            tex,
>            smel,
>            siz,
>            pric,
>            SD_colb,
>            SD_colw,
>            SD_colc,
>            SD_tast,
>            SD_tex,
>            SD_siz,
>            SD_smel,
>            SD_pric
>            ;start=b
>            ;Var=Varb
>            ;Fn1=-1*(colb/pric)
>            ;Fn2=-1*(colw/pric)
>            ;Fn3=-1*(colc/pric)
>            ;Fn4=-1*(tast/pric)
>            ;Fn5=-1*(tex/pric)
>            ;Fn6=-1*(siz/pric)
>            ;Fn7=-1*(smel/pric)$
> 
> 
> When I double click the B matrix, I see one column with 15 entries in it.
> How am  I supposed to use the entries in the specification above, since I
> have arleady specified b as starting values?
> 
> Thanks,
> 
> Medard
> 
> 
> 
> On Tue, Jul 24, 2018 at 8:42 PM, William Greene via Limdep <
> limdep at mailman.sydney.edu.au> wrote:
> 
>> Medard.  Look at your output in the output window.  Then, double click B in
>> the
>> project window, and you will see what is contained in B in the right
>> order.  When
>> you use ;Start=B ; Var = Varb you can then use the right ;Labels = list...
>> THEN
>> set up your functions.
>> /.B. Greene
>> 
>> On Tue, Jul 24, 2018 at 12:34 PM, medard kakuru via Limdep <
>> limdep at mailman.sydney.edu.au> wrote:
>> 
>>> Thanks Bill.
>>> However, I seem not to understand the matching and the submission you are
>>> talking about. Kindly give me a reference in the nlogit manual so that I
>>> read for more understanding.
>>> Thanks.
>>> Medard
>>> On Tue, Jul 24, 2018, 19:03 William Greene via Limdep <
>>> limdep at mailman.sydney.edu.au> wrote:
>>> 
>>>> Yes you can.  After estimation, double click on the B matrix and see
>> what
>>>> is in there.
>>>> Match it up against your output.  Then submit B and VARB as the
>>> parameters
>>>> and
>>>> variance for the command.
>>>> /B. Greene
>>>> 
>>>> On Tue, Jul 24, 2018 at 11:52 AM, medard kakuru via Limdep <
>>>> limdep at mailman.sydney.edu.au> wrote:
>>>> 
>>>>> So i can't estimate wtp using the Wald command if one of the
>>> coeffecients
>>>>> is nonrandom. I also get the same error message when I apply the wald
>>>>> command after estimating a gmxl in utility space. Where could I be
>>> going
>>>>> wrong?
>>>>> 
>>>>> Thanks in advance.
>>>>> Medard
>>>>> 
>>>>> On Tue, Jul 24, 2018, 17:51 William Greene via Limdep <
>>>>> limdep at mailman.sydney.edu.au> wrote:
>>>>> 
>>>>>> exactly right.  I agree
>>>>>> Bill Greene
>>>>>> 
>>>>>> On Tue, Jul 24, 2018 at 10:01 AM, Fredrik Carlsson <
>>>>>> fredrik.carlsson at economics.gu.se> wrote:
>>>>>> 
>>>>>>> You have one less parameter, so reduce the number of parameters
>> in
>>>> the
>>>>>>> labels part of the Wald-command
>>>>>>> 
>>>>>>> Fredrik
>>>>>>> 
>>>>>>> Skickat fr?n min iPhone
>>>>>>> 
>>>>>>>> 24 juli 2018 kl. 15:53 skrev medard kakuru via Limdep <
>>>>>>> limdep at mailman.sydney.edu.au>:
>>>>>>>> 
>>>>>>>> Thanks Bill.
>>>>>>>> I am facing another challenge. I use the wald command to
>> estimate
>>>> wtp
>>>>>>> after
>>>>>>>> estimating a mixed logit with all non-attribute coefficients
>>> given
>>>> a
>>>>>>> normal
>>>>>>>> distribution and the syntax works. Since the standard deviation
>>> for
>>>>> one
>>>>>>>> attribute was not significant, I re-specify the model and make
>>> that
>>>>>>>> attribute non-random. Running the wald command after this
>>>>> specification
>>>>>>>> gives me an error message that "wrong number of start values -
>>> need
>>>>> one
>>>>>>> for
>>>>>>>> each label". What could be the problem?
>>>>>>>> 
>>>>>>>> Thanks.
>>>>>>>> 
>>>>>>>> Medard
>>>>>>>> 
>>>>>>>> On Sun, Jul 22, 2018 at 12:35 AM, William Greene via Limdep <
>>>>>>>> limdep at mailman.sydney.edu.au> wrote:
>>>>>>>> 
>>>>>>>>> Medard.  WTP for all variants of the RP logit model is
>> described
>>>> in
>>>>>>>>> Chapter N29.  That would be good for the S-MNL and GMXL.  I'm
>>>>>>>>> not sure what the G-MNL model is.  WTP is generally a ratio of
>>>>>>>>> coefficients, though in RP models, the WTP is computed for
>> each
>>>>>>>>> individual.  P values for LR statistics are generally not
>>>> computed.
>>>>>>>>> I'm not sure what the P-value at 5% is.  You can use CALC to
>>> look
>>>>>>>>> up critical values for chi-squared if you wish.  The function
>>>>>>>>> CTB(prob,df) returns the critical value for probability prob
>>> with
>>>>>>>>> degrees of freedom df.
>>>>>>>>> Regards
>>>>>>>>> /Bill Greene
>>>>>>>>> 
>>>>>>>>> On Fri, Jul 20, 2018 at 5:22 AM, medard kakuru via Limdep <
>>>>>>>>> limdep at mailman.sydney.edu.au> wrote:
>>>>>>>>> 
>>>>>>>>>> Dear All,
>>>>>>>>>> Kindly help me with the syntax for wtp in preference space. I
>>> am
>>>>>>> running
>>>>>>>>>> S-MNL, G-MNL and the GMXL models and want to compare WTP
>>>> estimates
>>>>>> for
>>>>>>>>> the
>>>>>>>>>> three models. I also want to compare these estimates with
>> those
>>>>>>> obtained
>>>>>>>>>> from wtp-space model estimations. I understand that for a
>>> simple
>>>>> MXL
>>>>>>>>> model,
>>>>>>>>>> the syntax for wtp is just a ratio of attribute and cost
>>>>>> coefficients.
>>>>>>> Is
>>>>>>>>>> it the case with the models I am estimating? I expected to
>> find
>>>> the
>>>>>>>>> syntax
>>>>>>>>>> in the Nlogit manual (section N33) but it's not listed.
>>>>>>>>>> 
>>>>>>>>>> 
>>>>>>>>>> Secondly, I have seen the syntax for carrying out a
>>> loglikelihood
>>>>>> ratio
>>>>>>>>>> test and the syntax gives the LR statistic. How do i go
>> further
>>>> to
>>>>>> get
>>>>>>> a
>>>>>>>>>> p-value (say at 5%) for the statistic?
>>>>>>>>>> 
>>>>>>>>>> Thanks in advance.
>>>>>>>>>> 
>>>>>>>>>> Regards, Medard
>>>>>>>>>> _______________________________________________
>>>>>>>>>> Limdep site list
>>>>>>>>>> Limdep at mailman.sydney.edu.au
>>>>>>>>>> http://limdep.itls.usyd.edu.au
>>>>>>>>>> 
>>>>>>>>>> 
>>>>>>>>> 
>>>>>>>>> 
>>>>>>>>> --
>>>>>>>>> William Greene
>>>>>>>>> Department of Economics
>>>>>>>>> Stern School of Business, New York University
>>>>>>>>> 44 West 4 St., 7-90
>>>>>>>>> New York, NY, 10012
>>>>>>>>> URL: https://protect-au.mimecast.com/s/iN6HC4QZ1RFLO2YqtOFcSl?domain=people.stern.nyu.edu
>>>>>>>>> Email: wgreene at stern.nyu.edu
>>>>>>>>> Ph. +1.212.998.0876
>>>>>>>>> Editor in Chief: Journal of Productivity Analysis
>>>>>>>>> Editor in Chief: Foundations and Trends in Econometrics
>>>>>>>>> Associate Editor: Economics Letters
>>>>>>>>> Associate Editor: Journal of Business and Economic Statistics
>>>>>>>>> Associate Editor: Journal of Choice Modeling
>>>>>>>>> _______________________________________________
>>>>>>>>> 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
>>>>>>> 
>>>>>>> 
>>>>>> 
>>>>>> 
>>>>>> --
>>>>>> William Greene
>>>>>> Department of Economics
>>>>>> Stern School of Business, New York University
>>>>>> 44 West 4 St., 7-90
>>>>>> New York, NY, 10012
>>>>>> URL: https://protect-au.mimecast.com/s/iN6HC4QZ1RFLO2YqtOFcSl?domain=people.stern.nyu.edu
>>>>>> Email: wgreene at stern.nyu.edu
>>>>>> Ph. +1.212.998.0876
>>>>>> Editor in Chief: Journal of Productivity Analysis
>>>>>> Editor in Chief: Foundations and Trends in Econometrics
>>>>>> Associate Editor: Economics Letters
>>>>>> Associate Editor: Journal of Business and Economic Statistics
>>>>>> Associate Editor: Journal of Choice Modeling
>>>>>> _______________________________________________
>>>>>> 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
>>>>> 
>>>>> 
>>>> 
>>>> 
>>>> --
>>>> William Greene
>>>> Department of Economics
>>>> Stern School of Business, New York University
>>>> 44 West 4 St., 7-90
>>>> New York, NY, 10012
>>>> URL: https://protect-au.mimecast.com/s/iN6HC4QZ1RFLO2YqtOFcSl?domain=people.stern.nyu.edu
>>>> Email: wgreene at stern.nyu.edu
>>>> Ph. +1.212.998.0876
>>>> Editor in Chief: Journal of Productivity Analysis
>>>> Editor in Chief: Foundations and Trends in Econometrics
>>>> Associate Editor: Economics Letters
>>>> Associate Editor: Journal of Business and Economic Statistics
>>>> Associate Editor: Journal of Choice Modeling
>>>> _______________________________________________
>>>> 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
>>> 
>>> 
>> 
>> 
>> --
>> William Greene
>> Department of Economics
>> Stern School of Business, New York University
>> 44 West 4 St., 7-90
>> New York, NY, 10012
>> URL: https://protect-au.mimecast.com/s/iN6HC4QZ1RFLO2YqtOFcSl?domain=people.stern.nyu.edu
>> Email: wgreene at stern.nyu.edu
>> Ph. +1.212.998.0876
>> Editor in Chief: Journal of Productivity Analysis
>> Editor in Chief: Foundations and Trends in Econometrics
>> Associate Editor: Economics Letters
>> Associate Editor: Journal of Business and Economic Statistics
>> Associate Editor: Journal of Choice Modeling
>> _______________________________________________
>> 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
> 

From wgreene at stern.nyu.edu  Wed Jul 25 04:50:05 2018
From: wgreene at stern.nyu.edu (William Greene)
Date: Tue, 24 Jul 2018 14:50:05 -0400
Subject: [Limdep Nlogit List] WTp estimation
In-Reply-To: <CALwnpeR+N3e1FON0XX+zXKOHMARHTzWXgNRXH_eOHMKeknx62w@mail.gmail.com>
References: <CALwnpeRH25or1YDYW3JaQjT0Mz0ddiFoyoYxQpxVcgPv0JsekQ@mail.gmail.com>
	<CAEJPMR7JcmdByCuUsaifZDYZAb8b6POdf5p59TXzLuy9JtYmLA@mail.gmail.com>
	<CALwnpeTUApqJds1pE0-6tjyWRX4n6zrPmJCYesToGRHXcLU9=Q@mail.gmail.com>
	<22E7A439-EAF7-43E1-B7ED-AC0731F663EC@economics.gu.se>
	<CAEJPMR48nFWvLa1XkgSQiC48o_-m1QOjR4NaF5RpPS=V-Qffcg@mail.gmail.com>
	<CALwnpeSqDsM=Lo6EF-BN0-901p0qhZG3evA35EMNpAXhoLZtRw@mail.gmail.com>
	<CAEJPMR4jaO1gV-ua8MZZRe9-WjkwH0NsnngjgZxzx4ctfuE78w@mail.gmail.com>
	<CALwnpeQs5+DoyTHY4bxEWbN3rr0FU+whqr9WvT4mHfo4u+tgaQ@mail.gmail.com>
	<CAEJPMR6=szZ_rNuGVyTxmaJCoke6idN9=S9dzKgmU3QapaJ5dg@mail.gmail.com>
	<CALwnpeR+N3e1FON0XX+zXKOHMARHTzWXgNRXH_eOHMKeknx62w@mail.gmail.com>
Message-ID: <CAEJPMR6QSuA7nHydf+=tvBPtTY7ANERsd=+B+ZKqRXm4=xTmKQ@mail.gmail.com>

Medard.  You have 16 labels.  If B has 15 values in it, that is what
produced the
diagnostic.  You don't have to use all the parameters that you label.  But,
you have
to have the same number of labels as you do values.
/B. Greene

On Tue, Jul 24, 2018 at 1:56 PM, medard kakuru via Limdep <
limdep at mailman.sydney.edu.au> wrote:

> Dear Bill,
> Precisely, this is what I am doing.
>
> WALD; Labels=colb,
>             colw,
>             colc,
>             tast,
>             tex,
>             smel,
>             siz,
>             pric,
>             SD_colb,
>             SD_colw,
>             SD_colc,
>             SD_tast,
>             SD_tex,
>             SD_siz,
>             SD_smel,
>             SD_pric
>             ;start=b
>             ;Var=Varb
>             ;Fn1=-1*(colb/pric)
>             ;Fn2=-1*(colw/pric)
>             ;Fn3=-1*(colc/pric)
>             ;Fn4=-1*(tast/pric)
>             ;Fn5=-1*(tex/pric)
>             ;Fn6=-1*(siz/pric)
>             ;Fn7=-1*(smel/pric)$
>
>
> When I double click the B matrix, I see one column with 15 entries in it.
> How am  I supposed to use the entries in the specification above, since I
> have arleady specified b as starting values?
>
> Thanks,
>
> Medard
>
>
>
> On Tue, Jul 24, 2018 at 8:42 PM, William Greene via Limdep <
> limdep at mailman.sydney.edu.au> wrote:
>
> > Medard.  Look at your output in the output window.  Then, double click B
> in
> > the
> > project window, and you will see what is contained in B in the right
> > order.  When
> > you use ;Start=B ; Var = Varb you can then use the right ;Labels =
> list...
> > THEN
> > set up your functions.
> > /.B. Greene
> >
> > On Tue, Jul 24, 2018 at 12:34 PM, medard kakuru via Limdep <
> > limdep at mailman.sydney.edu.au> wrote:
> >
> > > Thanks Bill.
> > > However, I seem not to understand the matching and the submission you
> are
> > > talking about. Kindly give me a reference in the nlogit manual so that
> I
> > > read for more understanding.
> > > Thanks.
> > > Medard
> > > On Tue, Jul 24, 2018, 19:03 William Greene via Limdep <
> > > limdep at mailman.sydney.edu.au> wrote:
> > >
> > > > Yes you can.  After estimation, double click on the B matrix and see
> > what
> > > > is in there.
> > > > Match it up against your output.  Then submit B and VARB as the
> > > parameters
> > > > and
> > > > variance for the command.
> > > > /B. Greene
> > > >
> > > > On Tue, Jul 24, 2018 at 11:52 AM, medard kakuru via Limdep <
> > > > limdep at mailman.sydney.edu.au> wrote:
> > > >
> > > > > So i can't estimate wtp using the Wald command if one of the
> > > coeffecients
> > > > > is nonrandom. I also get the same error message when I apply the
> wald
> > > > > command after estimating a gmxl in utility space. Where could I be
> > > going
> > > > > wrong?
> > > > >
> > > > > Thanks in advance.
> > > > > Medard
> > > > >
> > > > > On Tue, Jul 24, 2018, 17:51 William Greene via Limdep <
> > > > > limdep at mailman.sydney.edu.au> wrote:
> > > > >
> > > > > > exactly right.  I agree
> > > > > > Bill Greene
> > > > > >
> > > > > > On Tue, Jul 24, 2018 at 10:01 AM, Fredrik Carlsson <
> > > > > > fredrik.carlsson at economics.gu.se> wrote:
> > > > > >
> > > > > > > You have one less parameter, so reduce the number of parameters
> > in
> > > > the
> > > > > > > labels part of the Wald-command
> > > > > > >
> > > > > > > Fredrik
> > > > > > >
> > > > > > > Skickat fr?n min iPhone
> > > > > > >
> > > > > > > > 24 juli 2018 kl. 15:53 skrev medard kakuru via Limdep <
> > > > > > > limdep at mailman.sydney.edu.au>:
> > > > > > > >
> > > > > > > > Thanks Bill.
> > > > > > > > I am facing another challenge. I use the wald command to
> > estimate
> > > > wtp
> > > > > > > after
> > > > > > > > estimating a mixed logit with all non-attribute coefficients
> > > given
> > > > a
> > > > > > > normal
> > > > > > > > distribution and the syntax works. Since the standard
> deviation
> > > for
> > > > > one
> > > > > > > > attribute was not significant, I re-specify the model and
> make
> > > that
> > > > > > > > attribute non-random. Running the wald command after this
> > > > > specification
> > > > > > > > gives me an error message that "wrong number of start values
> -
> > > need
> > > > > one
> > > > > > > for
> > > > > > > > each label". What could be the problem?
> > > > > > > >
> > > > > > > > Thanks.
> > > > > > > >
> > > > > > > > Medard
> > > > > > > >
> > > > > > > > On Sun, Jul 22, 2018 at 12:35 AM, William Greene via Limdep <
> > > > > > > > limdep at mailman.sydney.edu.au> wrote:
> > > > > > > >
> > > > > > > >> Medard.  WTP for all variants of the RP logit model is
> > described
> > > > in
> > > > > > > >> Chapter N29.  That would be good for the S-MNL and GMXL.
> I'm
> > > > > > > >> not sure what the G-MNL model is.  WTP is generally a ratio
> of
> > > > > > > >> coefficients, though in RP models, the WTP is computed for
> > each
> > > > > > > >> individual.  P values for LR statistics are generally not
> > > > computed.
> > > > > > > >> I'm not sure what the P-value at 5% is.  You can use CALC to
> > > look
> > > > > > > >> up critical values for chi-squared if you wish.  The
> function
> > > > > > > >> CTB(prob,df) returns the critical value for probability prob
> > > with
> > > > > > > >> degrees of freedom df.
> > > > > > > >> Regards
> > > > > > > >> /Bill Greene
> > > > > > > >>
> > > > > > > >> On Fri, Jul 20, 2018 at 5:22 AM, medard kakuru via Limdep <
> > > > > > > >> limdep at mailman.sydney.edu.au> wrote:
> > > > > > > >>
> > > > > > > >>> Dear All,
> > > > > > > >>> Kindly help me with the syntax for wtp in preference
> space. I
> > > am
> > > > > > > running
> > > > > > > >>> S-MNL, G-MNL and the GMXL models and want to compare WTP
> > > > estimates
> > > > > > for
> > > > > > > >> the
> > > > > > > >>> three models. I also want to compare these estimates with
> > those
> > > > > > > obtained
> > > > > > > >>> from wtp-space model estimations. I understand that for a
> > > simple
> > > > > MXL
> > > > > > > >> model,
> > > > > > > >>> the syntax for wtp is just a ratio of attribute and cost
> > > > > > coefficients.
> > > > > > > Is
> > > > > > > >>> it the case with the models I am estimating? I expected to
> > find
> > > > the
> > > > > > > >> syntax
> > > > > > > >>> in the Nlogit manual (section N33) but it's not listed.
> > > > > > > >>>
> > > > > > > >>>
> > > > > > > >>> Secondly, I have seen the syntax for carrying out a
> > > loglikelihood
> > > > > > ratio
> > > > > > > >>> test and the syntax gives the LR statistic. How do i go
> > further
> > > > to
> > > > > > get
> > > > > > > a
> > > > > > > >>> p-value (say at 5%) for the statistic?
> > > > > > > >>>
> > > > > > > >>> Thanks in advance.
> > > > > > > >>>
> > > > > > > >>> Regards, Medard
> > > > > > > >>> _______________________________________________
> > > > > > > >>> Limdep site list
> > > > > > > >>> Limdep at mailman.sydney.edu.au
> > > > > > > >>> http://limdep.itls.usyd.edu.au
> > > > > > > >>>
> > > > > > > >>>
> > > > > > > >>
> > > > > > > >>
> > > > > > > >> --
> > > > > > > >> William Greene
> > > > > > > >> Department of Economics
> > > > > > > >> Stern School of Business, New York University
> > > > > > > >> 44 West 4 St., 7-90
> > > > > > > >> New York, NY, 10012
> > > > > > > >> URL: https://protect-au.mimecast.com/s/5Mv5Cq7BKYtm3gZjtZ4Ubj?domain=people.stern.nyu.edu
> > > > > > > >> Email: wgreene at stern.nyu.edu
> > > > > > > >> Ph. +1.212.998.0876
> > > > > > > >> Editor in Chief: Journal of Productivity Analysis
> > > > > > > >> Editor in Chief: Foundations and Trends in Econometrics
> > > > > > > >> Associate Editor: Economics Letters
> > > > > > > >> Associate Editor: Journal of Business and Economic
> Statistics
> > > > > > > >> Associate Editor: Journal of Choice Modeling
> > > > > > > >> _______________________________________________
> > > > > > > >> 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
> > > > > > >
> > > > > > >
> > > > > >
> > > > > >
> > > > > > --
> > > > > > William Greene
> > > > > > Department of Economics
> > > > > > Stern School of Business, New York University
> > > > > > 44 West 4 St., 7-90
> > > > > > New York, NY, 10012
> > > > > > URL: https://protect-au.mimecast.com/s/5Mv5Cq7BKYtm3gZjtZ4Ubj?domain=people.stern.nyu.edu
> > > > > > Email: wgreene at stern.nyu.edu
> > > > > > Ph. +1.212.998.0876
> > > > > > Editor in Chief: Journal of Productivity Analysis
> > > > > > Editor in Chief: Foundations and Trends in Econometrics
> > > > > > Associate Editor: Economics Letters
> > > > > > Associate Editor: Journal of Business and Economic Statistics
> > > > > > Associate Editor: Journal of Choice Modeling
> > > > > > _______________________________________________
> > > > > > 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
> > > > >
> > > > >
> > > >
> > > >
> > > > --
> > > > William Greene
> > > > Department of Economics
> > > > Stern School of Business, New York University
> > > > 44 West 4 St., 7-90
> > > > New York, NY, 10012
> > > > URL: https://protect-au.mimecast.com/s/5Mv5Cq7BKYtm3gZjtZ4Ubj?domain=people.stern.nyu.edu
> > > > Email: wgreene at stern.nyu.edu
> > > > Ph. +1.212.998.0876
> > > > Editor in Chief: Journal of Productivity Analysis
> > > > Editor in Chief: Foundations and Trends in Econometrics
> > > > Associate Editor: Economics Letters
> > > > Associate Editor: Journal of Business and Economic Statistics
> > > > Associate Editor: Journal of Choice Modeling
> > > > _______________________________________________
> > > > 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
> > >
> > >
> >
> >
> > --
> > William Greene
> > Department of Economics
> > Stern School of Business, New York University
> > 44 West 4 St., 7-90
> > New York, NY, 10012
> > URL: https://protect-au.mimecast.com/s/5Mv5Cq7BKYtm3gZjtZ4Ubj?domain=people.stern.nyu.edu
> > Email: wgreene at stern.nyu.edu
> > Ph. +1.212.998.0876
> > Editor in Chief: Journal of Productivity Analysis
> > Editor in Chief: Foundations and Trends in Econometrics
> > Associate Editor: Economics Letters
> > Associate Editor: Journal of Business and Economic Statistics
> > Associate Editor: Journal of Choice Modeling
> > _______________________________________________
> > 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
>
>


-- 
William Greene
Department of Economics
Stern School of Business, New York University
44 West 4 St., 7-90
New York, NY, 10012
URL: https://protect-au.mimecast.com/s/5Mv5Cq7BKYtm3gZjtZ4Ubj?domain=people.stern.nyu.edu
Email: wgreene at stern.nyu.edu
Ph. +1.212.998.0876
Editor in Chief: Journal of Productivity Analysis
Editor in Chief: Foundations and Trends in Econometrics
Associate Editor: Economics Letters
Associate Editor: Journal of Business and Economic Statistics
Associate Editor: Journal of Choice Modeling

From wgreene at stern.nyu.edu  Wed Jul 25 04:50:37 2018
From: wgreene at stern.nyu.edu (William Greene)
Date: Tue, 24 Jul 2018 14:50:37 -0400
Subject: [Limdep Nlogit List] WTp estimation
In-Reply-To: <A00AD1FA-9151-4EC0-8B03-7479D7F73D44@economics.gu.se>
References: <CALwnpeRH25or1YDYW3JaQjT0Mz0ddiFoyoYxQpxVcgPv0JsekQ@mail.gmail.com>
	<CAEJPMR7JcmdByCuUsaifZDYZAb8b6POdf5p59TXzLuy9JtYmLA@mail.gmail.com>
	<CALwnpeTUApqJds1pE0-6tjyWRX4n6zrPmJCYesToGRHXcLU9=Q@mail.gmail.com>
	<22E7A439-EAF7-43E1-B7ED-AC0731F663EC@economics.gu.se>
	<CAEJPMR48nFWvLa1XkgSQiC48o_-m1QOjR4NaF5RpPS=V-Qffcg@mail.gmail.com>
	<CALwnpeSqDsM=Lo6EF-BN0-901p0qhZG3evA35EMNpAXhoLZtRw@mail.gmail.com>
	<CAEJPMR4jaO1gV-ua8MZZRe9-WjkwH0NsnngjgZxzx4ctfuE78w@mail.gmail.com>
	<CALwnpeQs5+DoyTHY4bxEWbN3rr0FU+whqr9WvT4mHfo4u+tgaQ@mail.gmail.com>
	<CAEJPMR6=szZ_rNuGVyTxmaJCoke6idN9=S9dzKgmU3QapaJ5dg@mail.gmail.com>
	<CALwnpeR+N3e1FON0XX+zXKOHMARHTzWXgNRXH_eOHMKeknx62w@mail.gmail.com>
	<A00AD1FA-9151-4EC0-8B03-7479D7F73D44@economics.gu.se>
Message-ID: <CAEJPMR5rK5yVu2-+dFDjKT=H6wYgK57txX=BEMuZPTb0W=cHGQ@mail.gmail.com>

That looks right to me.
/Bill Greene

On Tue, Jul 24, 2018 at 2:03 PM, Fredrik Carlsson <
fredrik.carlsson at economics.gu.se> wrote:

> You should most likely take away SD_pric from labels. I assume this was
> the label for the random price coefficient that is now fixed instead
>
> Fredrik
>
> Skickat fr?n min iPhone
>
> > 24 juli 2018 kl. 19:56 skrev medard kakuru via Limdep <
> limdep at mailman.sydney.edu.au>:
> >
> > Dear Bill,
> > Precisely, this is what I am doing.
> >
> > WALD; Labels=colb,
> >            colw,
> >            colc,
> >            tast,
> >            tex,
> >            smel,
> >            siz,
> >            pric,
> >            SD_colb,
> >            SD_colw,
> >            SD_colc,
> >            SD_tast,
> >            SD_tex,
> >            SD_siz,
> >            SD_smel,
> >            SD_pric
> >            ;start=b
> >            ;Var=Varb
> >            ;Fn1=-1*(colb/pric)
> >            ;Fn2=-1*(colw/pric)
> >            ;Fn3=-1*(colc/pric)
> >            ;Fn4=-1*(tast/pric)
> >            ;Fn5=-1*(tex/pric)
> >            ;Fn6=-1*(siz/pric)
> >            ;Fn7=-1*(smel/pric)$
> >
> >
> > When I double click the B matrix, I see one column with 15 entries in it.
> > How am  I supposed to use the entries in the specification above, since I
> > have arleady specified b as starting values?
> >
> > Thanks,
> >
> > Medard
> >
> >
> >
> > On Tue, Jul 24, 2018 at 8:42 PM, William Greene via Limdep <
> > limdep at mailman.sydney.edu.au> wrote:
> >
> >> Medard.  Look at your output in the output window.  Then, double click
> B in
> >> the
> >> project window, and you will see what is contained in B in the right
> >> order.  When
> >> you use ;Start=B ; Var = Varb you can then use the right ;Labels =
> list...
> >> THEN
> >> set up your functions.
> >> /.B. Greene
> >>
> >> On Tue, Jul 24, 2018 at 12:34 PM, medard kakuru via Limdep <
> >> limdep at mailman.sydney.edu.au> wrote:
> >>
> >>> Thanks Bill.
> >>> However, I seem not to understand the matching and the submission you
> are
> >>> talking about. Kindly give me a reference in the nlogit manual so that
> I
> >>> read for more understanding.
> >>> Thanks.
> >>> Medard
> >>> On Tue, Jul 24, 2018, 19:03 William Greene via Limdep <
> >>> limdep at mailman.sydney.edu.au> wrote:
> >>>
> >>>> Yes you can.  After estimation, double click on the B matrix and see
> >> what
> >>>> is in there.
> >>>> Match it up against your output.  Then submit B and VARB as the
> >>> parameters
> >>>> and
> >>>> variance for the command.
> >>>> /B. Greene
> >>>>
> >>>> On Tue, Jul 24, 2018 at 11:52 AM, medard kakuru via Limdep <
> >>>> limdep at mailman.sydney.edu.au> wrote:
> >>>>
> >>>>> So i can't estimate wtp using the Wald command if one of the
> >>> coeffecients
> >>>>> is nonrandom. I also get the same error message when I apply the wald
> >>>>> command after estimating a gmxl in utility space. Where could I be
> >>> going
> >>>>> wrong?
> >>>>>
> >>>>> Thanks in advance.
> >>>>> Medard
> >>>>>
> >>>>> On Tue, Jul 24, 2018, 17:51 William Greene via Limdep <
> >>>>> limdep at mailman.sydney.edu.au> wrote:
> >>>>>
> >>>>>> exactly right.  I agree
> >>>>>> Bill Greene
> >>>>>>
> >>>>>> On Tue, Jul 24, 2018 at 10:01 AM, Fredrik Carlsson <
> >>>>>> fredrik.carlsson at economics.gu.se> wrote:
> >>>>>>
> >>>>>>> You have one less parameter, so reduce the number of parameters
> >> in
> >>>> the
> >>>>>>> labels part of the Wald-command
> >>>>>>>
> >>>>>>> Fredrik
> >>>>>>>
> >>>>>>> Skickat fr?n min iPhone
> >>>>>>>
> >>>>>>>> 24 juli 2018 kl. 15:53 skrev medard kakuru via Limdep <
> >>>>>>> limdep at mailman.sydney.edu.au>:
> >>>>>>>>
> >>>>>>>> Thanks Bill.
> >>>>>>>> I am facing another challenge. I use the wald command to
> >> estimate
> >>>> wtp
> >>>>>>> after
> >>>>>>>> estimating a mixed logit with all non-attribute coefficients
> >>> given
> >>>> a
> >>>>>>> normal
> >>>>>>>> distribution and the syntax works. Since the standard deviation
> >>> for
> >>>>> one
> >>>>>>>> attribute was not significant, I re-specify the model and make
> >>> that
> >>>>>>>> attribute non-random. Running the wald command after this
> >>>>> specification
> >>>>>>>> gives me an error message that "wrong number of start values -
> >>> need
> >>>>> one
> >>>>>>> for
> >>>>>>>> each label". What could be the problem?
> >>>>>>>>
> >>>>>>>> Thanks.
> >>>>>>>>
> >>>>>>>> Medard
> >>>>>>>>
> >>>>>>>> On Sun, Jul 22, 2018 at 12:35 AM, William Greene via Limdep <
> >>>>>>>> limdep at mailman.sydney.edu.au> wrote:
> >>>>>>>>
> >>>>>>>>> Medard.  WTP for all variants of the RP logit model is
> >> described
> >>>> in
> >>>>>>>>> Chapter N29.  That would be good for the S-MNL and GMXL.  I'm
> >>>>>>>>> not sure what the G-MNL model is.  WTP is generally a ratio of
> >>>>>>>>> coefficients, though in RP models, the WTP is computed for
> >> each
> >>>>>>>>> individual.  P values for LR statistics are generally not
> >>>> computed.
> >>>>>>>>> I'm not sure what the P-value at 5% is.  You can use CALC to
> >>> look
> >>>>>>>>> up critical values for chi-squared if you wish.  The function
> >>>>>>>>> CTB(prob,df) returns the critical value for probability prob
> >>> with
> >>>>>>>>> degrees of freedom df.
> >>>>>>>>> Regards
> >>>>>>>>> /Bill Greene
> >>>>>>>>>
> >>>>>>>>> On Fri, Jul 20, 2018 at 5:22 AM, medard kakuru via Limdep <
> >>>>>>>>> limdep at mailman.sydney.edu.au> wrote:
> >>>>>>>>>
> >>>>>>>>>> Dear All,
> >>>>>>>>>> Kindly help me with the syntax for wtp in preference space. I
> >>> am
> >>>>>>> running
> >>>>>>>>>> S-MNL, G-MNL and the GMXL models and want to compare WTP
> >>>> estimates
> >>>>>> for
> >>>>>>>>> the
> >>>>>>>>>> three models. I also want to compare these estimates with
> >> those
> >>>>>>> obtained
> >>>>>>>>>> from wtp-space model estimations. I understand that for a
> >>> simple
> >>>>> MXL
> >>>>>>>>> model,
> >>>>>>>>>> the syntax for wtp is just a ratio of attribute and cost
> >>>>>> coefficients.
> >>>>>>> Is
> >>>>>>>>>> it the case with the models I am estimating? I expected to
> >> find
> >>>> the
> >>>>>>>>> syntax
> >>>>>>>>>> in the Nlogit manual (section N33) but it's not listed.
> >>>>>>>>>>
> >>>>>>>>>>
> >>>>>>>>>> Secondly, I have seen the syntax for carrying out a
> >>> loglikelihood
> >>>>>> ratio
> >>>>>>>>>> test and the syntax gives the LR statistic. How do i go
> >> further
> >>>> to
> >>>>>> get
> >>>>>>> a
> >>>>>>>>>> p-value (say at 5%) for the statistic?
> >>>>>>>>>>
> >>>>>>>>>> Thanks in advance.
> >>>>>>>>>>
> >>>>>>>>>> Regards, Medard
> >>>>>>>>>> _______________________________________________
> >>>>>>>>>> Limdep site list
> >>>>>>>>>> Limdep at mailman.sydney.edu.au
> >>>>>>>>>> http://limdep.itls.usyd.edu.au
> >>>>>>>>>>
> >>>>>>>>>>
> >>>>>>>>>
> >>>>>>>>>
> >>>>>>>>> --
> >>>>>>>>> William Greene
> >>>>>>>>> Department of Economics
> >>>>>>>>> Stern School of Business, New York University
> >>>>>>>>> 44 West 4 St., 7-90
> >>>>>>>>> New York, NY, 10012
> >>>>>>>>> URL: https://protect-au.mimecast.com/s/JRujCJyp0qh0vkExsV5FgU?domain=people.stern.nyu.edu
> >>>>>>>>> Email: wgreene at stern.nyu.edu
> >>>>>>>>> Ph. +1.212.998.0876
> >>>>>>>>> Editor in Chief: Journal of Productivity Analysis
> >>>>>>>>> Editor in Chief: Foundations and Trends in Econometrics
> >>>>>>>>> Associate Editor: Economics Letters
> >>>>>>>>> Associate Editor: Journal of Business and Economic Statistics
> >>>>>>>>> Associate Editor: Journal of Choice Modeling
> >>>>>>>>> _______________________________________________
> >>>>>>>>> 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
> >>>>>>>
> >>>>>>>
> >>>>>>
> >>>>>>
> >>>>>> --
> >>>>>> William Greene
> >>>>>> Department of Economics
> >>>>>> Stern School of Business, New York University
> >>>>>> 44 West 4 St., 7-90
> >>>>>> New York, NY, 10012
> >>>>>> URL: https://protect-au.mimecast.com/s/JRujCJyp0qh0vkExsV5FgU?domain=people.stern.nyu.edu
> >>>>>> Email: wgreene at stern.nyu.edu
> >>>>>> Ph. +1.212.998.0876
> >>>>>> Editor in Chief: Journal of Productivity Analysis
> >>>>>> Editor in Chief: Foundations and Trends in Econometrics
> >>>>>> Associate Editor: Economics Letters
> >>>>>> Associate Editor: Journal of Business and Economic Statistics
> >>>>>> Associate Editor: Journal of Choice Modeling
> >>>>>> _______________________________________________
> >>>>>> 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
> >>>>>
> >>>>>
> >>>>
> >>>>
> >>>> --
> >>>> William Greene
> >>>> Department of Economics
> >>>> Stern School of Business, New York University
> >>>> 44 West 4 St., 7-90
> >>>> New York, NY, 10012
> >>>> URL: https://protect-au.mimecast.com/s/JRujCJyp0qh0vkExsV5FgU?domain=people.stern.nyu.edu
> >>>> Email: wgreene at stern.nyu.edu
> >>>> Ph. +1.212.998.0876
> >>>> Editor in Chief: Journal of Productivity Analysis
> >>>> Editor in Chief: Foundations and Trends in Econometrics
> >>>> Associate Editor: Economics Letters
> >>>> Associate Editor: Journal of Business and Economic Statistics
> >>>> Associate Editor: Journal of Choice Modeling
> >>>> _______________________________________________
> >>>> 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
> >>>
> >>>
> >>
> >>
> >> --
> >> William Greene
> >> Department of Economics
> >> Stern School of Business, New York University
> >> 44 West 4 St., 7-90
> >> New York, NY, 10012
> >> URL: https://protect-au.mimecast.com/s/JRujCJyp0qh0vkExsV5FgU?domain=people.stern.nyu.edu
> >> Email: wgreene at stern.nyu.edu
> >> Ph. +1.212.998.0876
> >> Editor in Chief: Journal of Productivity Analysis
> >> Editor in Chief: Foundations and Trends in Econometrics
> >> Associate Editor: Economics Letters
> >> Associate Editor: Journal of Business and Economic Statistics
> >> Associate Editor: Journal of Choice Modeling
> >> _______________________________________________
> >> 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
>
>


-- 
William Greene
Department of Economics
Stern School of Business, New York University
44 West 4 St., 7-90
New York, NY, 10012
URL: https://protect-au.mimecast.com/s/JRujCJyp0qh0vkExsV5FgU?domain=people.stern.nyu.edu
Email: wgreene at stern.nyu.edu
Ph. +1.212.998.0876
Editor in Chief: Journal of Productivity Analysis
Editor in Chief: Foundations and Trends in Econometrics
Associate Editor: Economics Letters
Associate Editor: Journal of Business and Economic Statistics
Associate Editor: Journal of Choice Modeling

From medakseth at gmail.com  Wed Jul 25 16:01:51 2018
From: medakseth at gmail.com (medard kakuru)
Date: Wed, 25 Jul 2018 09:01:51 +0300
Subject: [Limdep Nlogit List] WTp estimation
In-Reply-To: <CAEJPMR5rK5yVu2-+dFDjKT=H6wYgK57txX=BEMuZPTb0W=cHGQ@mail.gmail.com>
References: <CALwnpeRH25or1YDYW3JaQjT0Mz0ddiFoyoYxQpxVcgPv0JsekQ@mail.gmail.com>
	<CAEJPMR7JcmdByCuUsaifZDYZAb8b6POdf5p59TXzLuy9JtYmLA@mail.gmail.com>
	<CALwnpeTUApqJds1pE0-6tjyWRX4n6zrPmJCYesToGRHXcLU9=Q@mail.gmail.com>
	<22E7A439-EAF7-43E1-B7ED-AC0731F663EC@economics.gu.se>
	<CAEJPMR48nFWvLa1XkgSQiC48o_-m1QOjR4NaF5RpPS=V-Qffcg@mail.gmail.com>
	<CALwnpeSqDsM=Lo6EF-BN0-901p0qhZG3evA35EMNpAXhoLZtRw@mail.gmail.com>
	<CAEJPMR4jaO1gV-ua8MZZRe9-WjkwH0NsnngjgZxzx4ctfuE78w@mail.gmail.com>
	<CALwnpeQs5+DoyTHY4bxEWbN3rr0FU+whqr9WvT4mHfo4u+tgaQ@mail.gmail.com>
	<CAEJPMR6=szZ_rNuGVyTxmaJCoke6idN9=S9dzKgmU3QapaJ5dg@mail.gmail.com>
	<CALwnpeR+N3e1FON0XX+zXKOHMARHTzWXgNRXH_eOHMKeknx62w@mail.gmail.com>
	<A00AD1FA-9151-4EC0-8B03-7479D7F73D44@economics.gu.se>
	<CAEJPMR5rK5yVu2-+dFDjKT=H6wYgK57txX=BEMuZPTb0W=cHGQ@mail.gmail.com>
Message-ID: <CALwnpeSL4bYCZ8HwZT=0CV_P1hWk6cn=-BH6KsDOobpPnX57iA@mail.gmail.com>

Dear Greene and Fredrik,
Your advice has sorted me out. Thanks.

Medard

On Tue, Jul 24, 2018 at 9:50 PM, William Greene via Limdep <
limdep at mailman.sydney.edu.au> wrote:

> That looks right to me.
> /Bill Greene
>
> On Tue, Jul 24, 2018 at 2:03 PM, Fredrik Carlsson <
> fredrik.carlsson at economics.gu.se> wrote:
>
> > You should most likely take away SD_pric from labels. I assume this was
> > the label for the random price coefficient that is now fixed instead
> >
> > Fredrik
> >
> > Skickat fr?n min iPhone
> >
> > > 24 juli 2018 kl. 19:56 skrev medard kakuru via Limdep <
> > limdep at mailman.sydney.edu.au>:
> > >
> > > Dear Bill,
> > > Precisely, this is what I am doing.
> > >
> > > WALD; Labels=colb,
> > >            colw,
> > >            colc,
> > >            tast,
> > >            tex,
> > >            smel,
> > >            siz,
> > >            pric,
> > >            SD_colb,
> > >            SD_colw,
> > >            SD_colc,
> > >            SD_tast,
> > >            SD_tex,
> > >            SD_siz,
> > >            SD_smel,
> > >            SD_pric
> > >            ;start=b
> > >            ;Var=Varb
> > >            ;Fn1=-1*(colb/pric)
> > >            ;Fn2=-1*(colw/pric)
> > >            ;Fn3=-1*(colc/pric)
> > >            ;Fn4=-1*(tast/pric)
> > >            ;Fn5=-1*(tex/pric)
> > >            ;Fn6=-1*(siz/pric)
> > >            ;Fn7=-1*(smel/pric)$
> > >
> > >
> > > When I double click the B matrix, I see one column with 15 entries in
> it.
> > > How am  I supposed to use the entries in the specification above,
> since I
> > > have arleady specified b as starting values?
> > >
> > > Thanks,
> > >
> > > Medard
> > >
> > >
> > >
> > > On Tue, Jul 24, 2018 at 8:42 PM, William Greene via Limdep <
> > > limdep at mailman.sydney.edu.au> wrote:
> > >
> > >> Medard.  Look at your output in the output window.  Then, double click
> > B in
> > >> the
> > >> project window, and you will see what is contained in B in the right
> > >> order.  When
> > >> you use ;Start=B ; Var = Varb you can then use the right ;Labels =
> > list...
> > >> THEN
> > >> set up your functions.
> > >> /.B. Greene
> > >>
> > >> On Tue, Jul 24, 2018 at 12:34 PM, medard kakuru via Limdep <
> > >> limdep at mailman.sydney.edu.au> wrote:
> > >>
> > >>> Thanks Bill.
> > >>> However, I seem not to understand the matching and the submission you
> > are
> > >>> talking about. Kindly give me a reference in the nlogit manual so
> that
> > I
> > >>> read for more understanding.
> > >>> Thanks.
> > >>> Medard
> > >>> On Tue, Jul 24, 2018, 19:03 William Greene via Limdep <
> > >>> limdep at mailman.sydney.edu.au> wrote:
> > >>>
> > >>>> Yes you can.  After estimation, double click on the B matrix and see
> > >> what
> > >>>> is in there.
> > >>>> Match it up against your output.  Then submit B and VARB as the
> > >>> parameters
> > >>>> and
> > >>>> variance for the command.
> > >>>> /B. Greene
> > >>>>
> > >>>> On Tue, Jul 24, 2018 at 11:52 AM, medard kakuru via Limdep <
> > >>>> limdep at mailman.sydney.edu.au> wrote:
> > >>>>
> > >>>>> So i can't estimate wtp using the Wald command if one of the
> > >>> coeffecients
> > >>>>> is nonrandom. I also get the same error message when I apply the
> wald
> > >>>>> command after estimating a gmxl in utility space. Where could I be
> > >>> going
> > >>>>> wrong?
> > >>>>>
> > >>>>> Thanks in advance.
> > >>>>> Medard
> > >>>>>
> > >>>>> On Tue, Jul 24, 2018, 17:51 William Greene via Limdep <
> > >>>>> limdep at mailman.sydney.edu.au> wrote:
> > >>>>>
> > >>>>>> exactly right.  I agree
> > >>>>>> Bill Greene
> > >>>>>>
> > >>>>>> On Tue, Jul 24, 2018 at 10:01 AM, Fredrik Carlsson <
> > >>>>>> fredrik.carlsson at economics.gu.se> wrote:
> > >>>>>>
> > >>>>>>> You have one less parameter, so reduce the number of parameters
> > >> in
> > >>>> the
> > >>>>>>> labels part of the Wald-command
> > >>>>>>>
> > >>>>>>> Fredrik
> > >>>>>>>
> > >>>>>>> Skickat fr?n min iPhone
> > >>>>>>>
> > >>>>>>>> 24 juli 2018 kl. 15:53 skrev medard kakuru via Limdep <
> > >>>>>>> limdep at mailman.sydney.edu.au>:
> > >>>>>>>>
> > >>>>>>>> Thanks Bill.
> > >>>>>>>> I am facing another challenge. I use the wald command to
> > >> estimate
> > >>>> wtp
> > >>>>>>> after
> > >>>>>>>> estimating a mixed logit with all non-attribute coefficients
> > >>> given
> > >>>> a
> > >>>>>>> normal
> > >>>>>>>> distribution and the syntax works. Since the standard deviation
> > >>> for
> > >>>>> one
> > >>>>>>>> attribute was not significant, I re-specify the model and make
> > >>> that
> > >>>>>>>> attribute non-random. Running the wald command after this
> > >>>>> specification
> > >>>>>>>> gives me an error message that "wrong number of start values -
> > >>> need
> > >>>>> one
> > >>>>>>> for
> > >>>>>>>> each label". What could be the problem?
> > >>>>>>>>
> > >>>>>>>> Thanks.
> > >>>>>>>>
> > >>>>>>>> Medard
> > >>>>>>>>
> > >>>>>>>> On Sun, Jul 22, 2018 at 12:35 AM, William Greene via Limdep <
> > >>>>>>>> limdep at mailman.sydney.edu.au> wrote:
> > >>>>>>>>
> > >>>>>>>>> Medard.  WTP for all variants of the RP logit model is
> > >> described
> > >>>> in
> > >>>>>>>>> Chapter N29.  That would be good for the S-MNL and GMXL.  I'm
> > >>>>>>>>> not sure what the G-MNL model is.  WTP is generally a ratio of
> > >>>>>>>>> coefficients, though in RP models, the WTP is computed for
> > >> each
> > >>>>>>>>> individual.  P values for LR statistics are generally not
> > >>>> computed.
> > >>>>>>>>> I'm not sure what the P-value at 5% is.  You can use CALC to
> > >>> look
> > >>>>>>>>> up critical values for chi-squared if you wish.  The function
> > >>>>>>>>> CTB(prob,df) returns the critical value for probability prob
> > >>> with
> > >>>>>>>>> degrees of freedom df.
> > >>>>>>>>> Regards
> > >>>>>>>>> /Bill Greene
> > >>>>>>>>>
> > >>>>>>>>> On Fri, Jul 20, 2018 at 5:22 AM, medard kakuru via Limdep <
> > >>>>>>>>> limdep at mailman.sydney.edu.au> wrote:
> > >>>>>>>>>
> > >>>>>>>>>> Dear All,
> > >>>>>>>>>> Kindly help me with the syntax for wtp in preference space. I
> > >>> am
> > >>>>>>> running
> > >>>>>>>>>> S-MNL, G-MNL and the GMXL models and want to compare WTP
> > >>>> estimates
> > >>>>>> for
> > >>>>>>>>> the
> > >>>>>>>>>> three models. I also want to compare these estimates with
> > >> those
> > >>>>>>> obtained
> > >>>>>>>>>> from wtp-space model estimations. I understand that for a
> > >>> simple
> > >>>>> MXL
> > >>>>>>>>> model,
> > >>>>>>>>>> the syntax for wtp is just a ratio of attribute and cost
> > >>>>>> coefficients.
> > >>>>>>> Is
> > >>>>>>>>>> it the case with the models I am estimating? I expected to
> > >> find
> > >>>> the
> > >>>>>>>>> syntax
> > >>>>>>>>>> in the Nlogit manual (section N33) but it's not listed.
> > >>>>>>>>>>
> > >>>>>>>>>>
> > >>>>>>>>>> Secondly, I have seen the syntax for carrying out a
> > >>> loglikelihood
> > >>>>>> ratio
> > >>>>>>>>>> test and the syntax gives the LR statistic. How do i go
> > >> further
> > >>>> to
> > >>>>>> get
> > >>>>>>> a
> > >>>>>>>>>> p-value (say at 5%) for the statistic?
> > >>>>>>>>>>
> > >>>>>>>>>> Thanks in advance.
> > >>>>>>>>>>
> > >>>>>>>>>> Regards, Medard
> > >>>>>>>>>> _______________________________________________
> > >>>>>>>>>> Limdep site list
> > >>>>>>>>>> Limdep at mailman.sydney.edu.au
> > >>>>>>>>>> http://limdep.itls.usyd.edu.au
> > >>>>>>>>>>
> > >>>>>>>>>>
> > >>>>>>>>>
> > >>>>>>>>>
> > >>>>>>>>> --
> > >>>>>>>>> William Greene
> > >>>>>>>>> Department of Economics
> > >>>>>>>>> Stern School of Business, New York University
> > >>>>>>>>> 44 West 4 St., 7-90
> > >>>>>>>>> New York, NY, 10012
> > >>>>>>>>> URL: https://protect-au.mimecast.com/s/ZcinCQnzP0tzVoRGIxuQyM?domain=people.stern.nyu.edu
> > >>>>>>>>> Email: wgreene at stern.nyu.edu
> > >>>>>>>>> Ph. +1.212.998.0876
> > >>>>>>>>> Editor in Chief: Journal of Productivity Analysis
> > >>>>>>>>> Editor in Chief: Foundations and Trends in Econometrics
> > >>>>>>>>> Associate Editor: Economics Letters
> > >>>>>>>>> Associate Editor: Journal of Business and Economic Statistics
> > >>>>>>>>> Associate Editor: Journal of Choice Modeling
> > >>>>>>>>> _______________________________________________
> > >>>>>>>>> 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
> > >>>>>>>
> > >>>>>>>
> > >>>>>>
> > >>>>>>
> > >>>>>> --
> > >>>>>> William Greene
> > >>>>>> Department of Economics
> > >>>>>> Stern School of Business, New York University
> > >>>>>> 44 West 4 St., 7-90
> > >>>>>> New York, NY, 10012
> > >>>>>> URL: https://protect-au.mimecast.com/s/ZcinCQnzP0tzVoRGIxuQyM?domain=people.stern.nyu.edu
> > >>>>>> Email: wgreene at stern.nyu.edu
> > >>>>>> Ph. +1.212.998.0876
> > >>>>>> Editor in Chief: Journal of Productivity Analysis
> > >>>>>> Editor in Chief: Foundations and Trends in Econometrics
> > >>>>>> Associate Editor: Economics Letters
> > >>>>>> Associate Editor: Journal of Business and Economic Statistics
> > >>>>>> Associate Editor: Journal of Choice Modeling
> > >>>>>> _______________________________________________
> > >>>>>> 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
> > >>>>>
> > >>>>>
> > >>>>
> > >>>>
> > >>>> --
> > >>>> William Greene
> > >>>> Department of Economics
> > >>>> Stern School of Business, New York University
> > >>>> 44 West 4 St., 7-90
> > >>>> New York, NY, 10012
> > >>>> URL: https://protect-au.mimecast.com/s/ZcinCQnzP0tzVoRGIxuQyM?domain=people.stern.nyu.edu
> > >>>> Email: wgreene at stern.nyu.edu
> > >>>> Ph. +1.212.998.0876
> > >>>> Editor in Chief: Journal of Productivity Analysis
> > >>>> Editor in Chief: Foundations and Trends in Econometrics
> > >>>> Associate Editor: Economics Letters
> > >>>> Associate Editor: Journal of Business and Economic Statistics
> > >>>> Associate Editor: Journal of Choice Modeling
> > >>>> _______________________________________________
> > >>>> 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
> > >>>
> > >>>
> > >>
> > >>
> > >> --
> > >> William Greene
> > >> Department of Economics
> > >> Stern School of Business, New York University
> > >> 44 West 4 St., 7-90
> > >> New York, NY, 10012
> > >> URL: https://protect-au.mimecast.com/s/ZcinCQnzP0tzVoRGIxuQyM?domain=people.stern.nyu.edu
> > >> Email: wgreene at stern.nyu.edu
> > >> Ph. +1.212.998.0876
> > >> Editor in Chief: Journal of Productivity Analysis
> > >> Editor in Chief: Foundations and Trends in Econometrics
> > >> Associate Editor: Economics Letters
> > >> Associate Editor: Journal of Business and Economic Statistics
> > >> Associate Editor: Journal of Choice Modeling
> > >> _______________________________________________
> > >> 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
> >
> >
>
>
> --
> William Greene
> Department of Economics
> Stern School of Business, New York University
> 44 West 4 St., 7-90
> New York, NY, 10012
> URL: https://protect-au.mimecast.com/s/ZcinCQnzP0tzVoRGIxuQyM?domain=people.stern.nyu.edu
> Email: wgreene at stern.nyu.edu
> Ph. +1.212.998.0876
> Editor in Chief: Journal of Productivity Analysis
> Editor in Chief: Foundations and Trends in Econometrics
> Associate Editor: Economics Letters
> Associate Editor: Journal of Business and Economic Statistics
> Associate Editor: Journal of Choice Modeling
> _______________________________________________
> Limdep site list
> Limdep at mailman.sydney.edu.au
> http://limdep.itls.usyd.edu.au
>
>

From medakseth at gmail.com  Wed Jul 25 20:22:47 2018
From: medakseth at gmail.com (medard kakuru)
Date: Wed, 25 Jul 2018 13:22:47 +0300
Subject: [Limdep Nlogit List] (no subject)
Message-ID: <CALwnpeSLev9wtZQa0Vng_sSDgJmmxvt6z5A6LVFsbYQw5K6usw@mail.gmail.com>

Dear colleagues,
I am facing another challenge.
I am estimating a GMXL with correlated attributes in wtp space. I have used
many distributions (normal, lognormal and traingular) but they all give the
same error message:

Initial iterations cannot improve function.Status=3
Error    805: Initial iterations cannot improve function.Status=3
Function=  .40647470237D+04, at entry,  .40647886835D+04 at exit
Error   1025: Failed to fit model. See earlier diagnostic.

Even when set gamma to 0 and 0.1, I still get the same error message.
Please advise.

Thanks in advance,

Medard

From medakseth at gmail.com  Wed Jul 25 20:31:41 2018
From: medakseth at gmail.com (medard kakuru)
Date: Wed, 25 Jul 2018 13:31:41 +0300
Subject: [Limdep Nlogit List] GMXL estimation
Message-ID: <CALwnpeTmQgTzGYQ96ddDu64yBG6+R45oanQ-QDY0Nk7=+OUFUw@mail.gmail.com>

 Dear colleagues,
I am facing another challenge.
I am estimating a GMXL with correlated attributes in wtp space. I have used
many distributions (normal, lognormal and traingular) but they all give the
same error message:

Initial iterations cannot improve function.Status=3
Error    805: Initial iterations cannot improve function.Status=3
Function=  .40647470237D+04, at entry,  .40647886835D+04 at exit
Error   1025: Failed to fit model. See earlier diagnostic.

Even when set gamma to 0 and 0.1, I still get the same error message.
Please advise.

Thanks in advance,

Medard