From y.ao at tue.nl  Fri Jan  5 02:03:29 2018
From: y.ao at tue.nl (Ao, Y.)
Date: Thu, 4 Jan 2018 15:03:29 +0000
Subject: [Limdep Nlogit List] (no subject)
Message-ID: <36B5EA20AB50B64FB79A85DEB0695C97EF8D2D@xserver30c.campus.tue.nl>

Dear.
I am a doctoral student,I am learning and practicing NLOGIT follow the introduction of NLOGIT5, but I can not find the exercising data, so could you please share the data for me?
Thank you very much and best regards.
Yibin

From carlesi at agrecon.univpm.it  Tue Jan  9 00:05:45 2018
From: carlesi at agrecon.univpm.it (carlesi at agrecon.univpm.it)
Date: Mon, 8 Jan 2018 14:05:45 +0100 (CET)
Subject: [Limdep Nlogit List] Remove contact
In-Reply-To: <CAEJPMR6Cv-MW1_uRt2detNcnfGQurkSTsoFr4NHPxWu7zihrxQ@mail.gmail.com>
References: <CACtF0aSxLagrYoirBk0Ltjz6xJWWEECYXMyTRNo+dH=g8qWFRQ@mail.gmail.com>
	<CAEJPMR6Cv-MW1_uRt2detNcnfGQurkSTsoFr4NHPxWu7zihrxQ@mail.gmail.com>
Message-ID: <53401.87.19.5.123.1515416745.squirrel@agrecon.univpm.it>

Please,
remove my contact from the mailing list.
Thank you.

Lorenzo


From richard.turner at imarketresearch.com  Tue Jan  9 03:31:35 2018
From: richard.turner at imarketresearch.com (Richard Turner)
Date: Mon, 8 Jan 2018 11:31:35 -0500
Subject: [Limdep Nlogit List] How to apply sampling weights in choice model?
Message-ID: <CADsq2CU27azT0Te7Q_69pcEs8_oCESPwpJHfkCOqJNZtQ9vWvg@mail.gmail.com>

Hello,

I am trying to apply sampling weights in a choice model. I have a variable
that is the inverse probability that certain survey respondents were
sampled from the population.

To apply this type of weight in to a choice model in NLOGIT, do I simply
use the command: ;wts= <name of inverse probability weight> ?

If so, I read in the LIMDEP/NLOGIT manual that in maximum likelihood
estimation, the terms in the log likelihood and its derivatives, and not
the data themselves, are multiplied by the weighting variable. I.e. Sum_i
w_1log(f_i). Is this the way NLOGIT applies sampling weights?

Finally, why would it be incorrect to multiply the predicted probabilities
of each choice set by the inverse probability weight and then rescale the
probabilities in each choice set to sum to 1?

Regards,

Richard

From miq at wne.uw.edu.pl  Tue Jan  9 04:13:12 2018
From: miq at wne.uw.edu.pl (=?UTF-8?Q?Miko=c5=82aj_Czajkowski?=)
Date: Mon, 8 Jan 2018 18:13:12 +0100
Subject: [Limdep Nlogit List] How to apply sampling weights in choice
 model?
In-Reply-To: <CADsq2CU27azT0Te7Q_69pcEs8_oCESPwpJHfkCOqJNZtQ9vWvg@mail.gmail.com>
References: <CADsq2CU27azT0Te7Q_69pcEs8_oCESPwpJHfkCOqJNZtQ9vWvg@mail.gmail.com>
Message-ID: <9b7f54de-e5d2-9fc2-822e-166c6352df96@wne.uw.edu.pl>


Dear Richard,

I do not know how are weights implemented in NLOGIT exactly, but the 
scaling variable w is probably scaled for mean = 1.
If I understand your question correctly - note that w*log(p) is not 
log(p*w) but rather log(p^w).

Best regards,
Mik



On 2018-01-08 17:31, Richard Turner wrote:
> Hello,
>
> I am trying to apply sampling weights in a choice model. I have a variable
> that is the inverse probability that certain survey respondents were
> sampled from the population.
>
> To apply this type of weight in to a choice model in NLOGIT, do I simply
> use the command: ;wts= <name of inverse probability weight> ?
>
> If so, I read in the LIMDEP/NLOGIT manual that in maximum likelihood
> estimation, the terms in the log likelihood and its derivatives, and not
> the data themselves, are multiplied by the weighting variable. I.e. Sum_i
> w_1log(f_i). Is this the way NLOGIT applies sampling weights?
>
> Finally, why would it be incorrect to multiply the predicted probabilities
> of each choice set by the inverse probability weight and then rescale the
> probabilities in each choice set to sum to 1?
>
> Regards,
>
> Richard
> _______________________________________________
> Limdep site list
> Limdep at mailman.sydney.edu.au
> http://limdep.itls.usyd.edu.au
>


From cvphani_kumar at yahoo.com  Tue Jan 23 20:53:24 2018
From: cvphani_kumar at yahoo.com (phani kumar)
Date: Tue, 23 Jan 2018 09:53:24 +0000 (UTC)
Subject: [Limdep Nlogit List] random individual effect despite not having
 panel data
References: <1209498032.2376616.1516701204108.ref@mail.yahoo.com>
Message-ID: <1209498032.2376616.1516701204108@mail.yahoo.com>

Hi,
I have a response variable that is multinomial? but categorical with 4 levels (eg: don't do anything, do A, do B, do both A&B.? I have one observation per participant. I was told that I can estimate random individual effect despite not having panel data in LIMDEP/NLOGIT. I would appreciate if someone confirm and suggest how (command) I can do it.?

Regards,Phani