[Limdep Nlogit List] WTp estimation

Tue Aug 14 23:49:38 AEST 2018

Hello Professor Greene:

I am sure you get swamped with econometric questions, but

I have looked through your textbook and have this particular question about

estimating a simultaneous equation system.

With an endogenous regressor,  in general an IV variable is needed, which

as you know searching for an appropriate one can prove challenging.

I have been under the impression that in the case of an endogenous regressor, the

common alternative has been to use the lagged value of the endogenous regressor,

since in general it is strongly correlated with the endogenous regresso but is less likely to be correlated with the other endogenous regressor.  I have thought this was a relatively uncontroversial assumption.

However,  I suppose the lagged value of the endogenous regressor can be viewed as an

IV variable, but I have not come across papers where the standard IV tests have been

applied to the use of a lagged endogenous variable as a  particular IV variable.   My question,  are these tests really needed when a lagged endogenous  variable has been used as instrument?   If no,  why?   If it is, Is it a common practice?   Finally  is there

a handy reference for this practice?

Thanks in advance.

Phil  Cyrenne

________________________________
From: Limdep <limdep-bounces at mailman.sydney.edu.au> on behalf of William Greene via Limdep <limdep at mailman.sydney.edu.au>
Sent: Tuesday, July 24, 2018 9:51:14 AM
To: Limdep and Nlogit Mailing List
Cc: William Greene
Subject: Re: [Limdep Nlogit List] WTp estimation

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 från 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/SXT7CQnzP0trQ7YVuxpOHa?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/SXT7CQnzP0trQ7YVuxpOHa?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