Constraining the # of attributes appearing in 2**n design

This forum is for posts that specifically focus on Ngene.

Moderators: Andrew Collins, Michiel Bliemer, johnr

Constraining the # of attributes appearing in 2**n design

Postby TCEagleInSV » Sat Oct 22, 2016 9:18 am

I think I know the answer to this because it is similar to the partial profile question posted earlier in this section. I have a 2**11 design where I want only 3 or 4 of the attributes to appear at one time. Is it possible to set up a rejection condition to reject runs of the design what to not meet that criteria? I am thinking of something like:

; reject
(a.att1=1)+(a.att2=1)+(a.att3=1)+(a.att4=1)+(a.att5=1)+(a.att6=1)+(a.att7=1)+(a.att8=1)+(a.att9=1)+(a.att10=1)+(a.att11=1)>4

Is such a conditional statement allowed in Ngene? I think I am going to here it is not possible yet...

Thank you !

Tom :D
TCEagleInSV
 
Posts: 2
Joined: Fri Oct 21, 2016 9:47 am

Re: Constraining the # of attributes appearing in 2**n desig

Postby Michiel Bliemer » Sun Oct 23, 2016 8:37 am

Dear Tom,

This is unfortunately not yet possible. I think your syntax with booleans is creative, but Ngene would not be able to evaluate it.

We do notice an increasing interest in availability designs (showing only a subset of alternatives) and partial profiles (showing only a subset of attributes), so it is definitely on our wish list.

Michiel
Michiel Bliemer
 
Posts: 1727
Joined: Tue Mar 31, 2009 4:13 pm


Return to Choice experiments - Ngene

Who is online

Users browsing this forum: No registered users and 5 guests

cron