Page 1 of 1

Partial choice set design

PostPosted: Wed Mar 04, 2020 11:39 pm
by Andrew
Dear Michiel,

we are planning a DCE using partial choice set design. In a former post "subset of alternatives" you mentioned

"there is another way of creating a partial choice set design without the need for an external candidate set, which involves reformulation of your utility functions. This is a new method and has not yet been published, but I am willing to explain."

Would you please explain the new method in more detail?

Recently I read a paper about fold-in, fold-out designs created in Ngene. Not sure whether you referred to this. However, the paper did not mention how it works.

Kind regards,
Andrew

Re: Partial choice set design

PostPosted: Thu Mar 05, 2020 8:43 am
by Michiel Bliemer
Hi Andrew,

I do not know what fold-in fold-out is, but the method that i am referred to is a trick you can use to rewrite a labelled experiment into an unlabelled experiment by creating indicator variables in Ngene. We have applied this a couple of times and seems to work well, although the number of constraints can grow very large and it may not work for very complex designs.

I have sent you a private message here on the forum so I can explain further.

Michiel