Undefined D-error

This forum is for posts covering broader stated choice experimental design issues.

Moderators: Andrew Collins, Michiel Bliemer, johnr

Undefined D-error

Postby nahar15 » Fri Jan 19, 2024 8:47 am

Hi Ngene team,
I am new to Ngene. Thanks for creating this amazing forum to get help.

My goal is to find WTP for three different types of vegetables (l,g,p) with three different pesticide levels (regular, 50% pesticides, organic). So, my design has two attributes with three levels each and four alternatives, including the opt-out option. I am using three price premiums for each. Now, I want three constraints: price of p>l, price of p>g, and price of g>l. However, adding these constraints with “require” gives a design after 1 iteration with an undefined d-error. The undefined d-error doesn’t make sense to me, as the designs are invalid. I have used the following syntax.

Design
;alts = alt1, alt2, alt3
;rows = 9
;eff = (mnl,d)
;alg=mfederov(candidates=2000)

; require:
alt3.p > alt2.g,
alt2.g > alt1.l,
alt3.p> alt1.l

;model:
U(alt1) = b1*T[1] + b2*V[1,2,3] + b3*l[1,2,3] /
U(alt2) = b1*U[1] + b2*V[1,2,3] + b3*g[1,2,3] /
U(alt3) = b1*W[1] + b2*V[1,2,3] + b3*p[1,2,3]
$

Why do I get an undefined d-error? The syntax runs fine without the constraints, but adding three constraints gives me an undefined d error.
I have also tried the “reject” syntax, which gave me the same result.
Any help is appreciated. Thanks.

Regards
Nabittu
nahar15
 
Posts: 1
Joined: Thu Jan 18, 2024 2:56 am

Re: Undefined D-error

Postby Michiel Bliemer » Fri Jan 19, 2024 9:14 am

You need to add the opt-out alternative in the list of alternatives:

;alts = alt1, alt2, alt3, optout

Otherwise you have constants for all alternatives and your model is not identified.

Michiel
Michiel Bliemer
 
Posts: 1733
Joined: Tue Mar 31, 2009 4:13 pm


Return to Choice experiments - general

Who is online

Users browsing this forum: No registered users and 19 guests