OOD designs, level specification and D-optimality

This forum is for posts that specifically focus on Ngene.

Moderators: Andrew Collins, Michiel Bliemer, johnr

OOD designs, level specification and D-optimality

Postby Ben Beardmore » Thu Dec 02, 2010 4:28 am

Hi there,
I'm trying to run an OOD design for a small choice experiment, consisting of 2 profiles, each consisting of two 3-level attributes and one 9-level attribute.

My code is below:
Design
;alts = alt1, alt2
;rows = 18
;block = 3
;orth = ood
;model:
U(alt1) = b0 + b1.dummy[0|0] * A[0,1,2] + b2.dummy[0|0] * B[0,1,2] + b3.dummy[0|0|0|0|0|0|0|0] * C[0,1,2,3,4,5,6,7,8] /
U(alt2) = b1 * A + b2 * B + b3 * C $


The design appears to be generated fine, but the D-Optimality remains "Undefined". I find this to be the case unless I keep all the attributes below 5 levels. Is this a known limitation of the software?
Ben Beardmore
 
Posts: 9
Joined: Wed Oct 21, 2009 2:52 pm

Re: OOD designs, level specification and D-optimality

Postby Andrew Collins » Mon Dec 13, 2010 4:15 pm

Hi Ben

The limitation in the software is with the number of levels supported for the ood calculation, where up to 6 levels are supported.

Andrew
Andrew Collins
 
Posts: 78
Joined: Sat Mar 28, 2009 4:48 pm


Return to Choice experiments - Ngene

Who is online

Users browsing this forum: No registered users and 32 guests