[Limdep Nlogit List] LimDep vs NLOGIT support?

Kandice L. Kleiber kleiberk at onid.orst.edu
Tue Apr 7 06:36:30 EST 2009

Hi Everyone -

I'm confused as to what LimDep 9.0 (not including NLOGIT) will support.  I'm
attempting to do sequential estimation of a nested logit model and I have
two different methods of coding, and I'm not sure if LimDep will support one
of them - I found the coding in the NLOGIT 3.0 manual, but I do not have
NLOGIT available.  Can someone please clarify??

My model looks like:
tree = land[corn(cc, sc, wc, oc), soy, wheat]  where cc, sc, wc, oc are 0-1
variables (where previous land came from) and corn, soy, and wheat are
proportion data.
Will LimDep 9.0 support this: ?*  *Or ... please see below this coding ... *
choices = cc, sc, wc, oc, soy, wheat;
ivb = incl0;
tree = land[corn(cc, sc, wc, oc), soy, wheat];
model: U(cc) = bcc + bpr41*pr41+bind1*ind1 ... /
           U(sc) = bsc +.../
           U(wc) = bwc +... /
          U(oc) =       bpr44*pr44+ ... /
        U(corn) = ac+ ... /
        U(soy) = as+ ... /
        U(wheat) =     aed3*ed3 + ....;
ivb = incl;

*I have tried to estimate [corn(cc, sc, wc, oc)] and save the inclusive
values.  I've tried just the basic multinomial logit model ... and in
setting up the second level to include the inclusive values, I need to
restrict the parameter on the inclusive values = 1, and only have the
inclusive value go into the parameter estimation for corn.  I'm not sure how
to incorporate this into my coding either. *

First step:
lhs = prop;
choices = cc, sc, wc, oc;
rhs = one, pr41, pr42, pr43, ind1, ind2, ind3, ... ;
ivb = incl0$

Second step:
lhs = corn, soy, wheat;
choices = corn, soy, wheat;
rhs = one, age1, age2, ... incl0 $

*Thank you for your help!

More information about the Limdep mailing list