[Limdep Nlogit List] Regarding customized ordered probit models

[Ganesh A R]

Hi all,

I am not sure if this is a mail id for posting in forums kindly ignore this
mail if this is not the right place to post


I am trying to build a *customized ordered probit model*. I am having
trouble building the probability and the log likelihood function

A brief description about the data :
1. The dependent variable is ordinal in nature with 3 alternatives - 1, 2 &
3
2. a1,a2 and a3 are indicator dummy variables for each alternative
3. u1,u2 and u3 are utility functions
4. mu1 and mu2 are threshold values

*for a constants only model, *

MAXIMIZE;Labels = b2,b3,mu1,mu2
;Start = 0,0,0,0
;Fcn = u1 = 0|
u2 = b2  |
u3 = b3  |
p1 = 1 - phi(u1-mu1) |
p2 = phi(u2-mu1) - phi(u2-mu2) |
p3 = phi(u3-mu2) |
llkhd = (a1*log(p1) + a2*log(p2) + a3*log(p3)) |
llkhd$


The model gives me error. I can understand that one reason might be because
I have not told the function that the ordinal variable values are 1, 2 and
3.
I would like to know what mistakes have I done in the above likelihood
function and how to rectify it.

Thanking you

Yours Sincerely

Ganesh

​PhD student

IIT Madras

​