[Limdep Nlogit List] plotting

Andreas Drichoutis eeco4dra at aua.gr
Tue Apr 7 03:21:12 EST 2009

Please see below the syntax I'm using to fit the model. I want to plot the
fitted probabilities over the time variable "period" (it takes values from 1
to 10) for values of the treat_pr=1 or 0. Note that there is also a random
variable (per_pric) which is the product of these two variables (in case it
matters). So how would I go about it? Do I need to use the fplot and how do
I treat the beta's from the scale parameters?


create ; per_pric=period*treat_pr $

namelist ;
onpos2,econpos3,econpos4 $

skip $

calc ; ran(12345) $ 

probit ; lhs=pr12 ; rhs=x1 ; pds=10;rpm ;
fcn=one(n),treat_pr(n),treat_tr(n),per_pric(n);marginal ;HALTON $


-----Original Message-----
From: limdep-bounces at limdep.itls.usyd.edu.au
[mailto:limdep-bounces at limdep.itls.usyd.edu.au] On Behalf Of William Greene
Sent: Monday, April 06, 2009 6:43 PM
To: Limdep and Nlogit Mailing List
Subject: Re: [Limdep Nlogit List] plotting


You'll have to fix the heterogeneity at its mean (zero) also.

So, your fitted probability is just

PHI(beta'xbar + c1*z1 + c2 * z2) for the specific values of

z1 and z2.

If they are discrete, however, you won't be plotting many

points, right?  Are you sure this is what you have in mind?


Bill Greene


----- Original Message -----

From: "Andreas Drichoutis" <adrihout at aua.gr>

To: limdep at limdep.itls.usyd.edu.au

Sent: Monday, April 6, 2009 7:29:51 AM GMT -05:00 US/Canada Eastern

Subject: [Limdep Nlogit List] plotting


Dear all,




How would one plot the fitted probabilities from a random effects panel

probit model that holds the other variables fixed at their means, while

varying two other discrete variables?









Limdep site list

Limdep at limdep.itls.usyd.edu.au



Limdep site list

Limdep at limdep.itls.usyd.edu.au


More information about the Limdep mailing list