[Limdep Nlogit List] different procedures to include interaction terms

[William Greene]

Lorenzo.
Superficially, the two specifications should produce the same results.
There are likely to be some small differences due to rounding error, as the
"interactions" are computed during estimation rather than in advance.
I am not sure that you will get the right answer for WTP with the first
specification, because it will not account for the roles of Var1 and Var2 in
computing the WTP.  You can, however, compute WTP with the second
specification, assuming WTP is A/C or B/C.  If it is supposed to be computed
as A/B, I don't think that is likely to give a good answer with either spec.
Do note, you don't want to use "B" as the name of a variable in your
specification.  B is a program reserved name for the parameter vector
(matrix) computed by the model.
Regards,
Bill Greene

On Mon, Jan 11, 2016 at 4:01 AM, <carlesi at agrecon.univpm.it> wrote:

> Dear Prof. Greene and LIMDEP/NLOGIT users,
>
> I collected data from an online survey. It included a discrete choice
> experiment.
> I wish to employ a RPL model taking into account interactions between
> choice attributes (A,B,C) and socio-economic variables (var1,var2).
>
> I am wondering which is the difference between:
>
> 1)
> CREATE; A_var1 = A*var1$
> CREATE; A_var2 = A*var2$
> CREATE; B_var1 = B*var1$
> CREATE; B_var2 = B*var2$
>
> RPLOGIT
> ; Lhs = choice
> ; CHOICES = car,bus,train
> ; Rhs = A,B,C,A_var1,A_var2,B_var1,B_var2
> ; Rh2 = one
> ; Fcn = A(n),B(n)
> ; Halton
> ; Pts = 100$
>
> and
>
> 2)
> RPLOGIT
> ; Lhs = choice
> ; CHOICES = car,bus,train
> ; Rhs = A,B,C
> ; Rh2 = one
> ; RPL = var1,var2
> ; Fcn = A(n),B(n)
> ; Halton
> ; Pts = 100$
>
> Moreover, is it possible to compute the WTP in the second case? Which is
> the right procedure to follow?
>
> Thank you in advance for your help,
>
> Lorenzo
>
> _______________________________________________
> Limdep site list
> Limdep at limdep.itls.usyd.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: http://people.stern.nyu.edu/wgreene
Email: wgreene at stern.nyu.edu
Ph. +1.212.998.0876