How to judge the utility balance of efficient design

This forum is for posts that specifically focus on Ngene.

Moderators: Andrew Collins, Michiel Bliemer, johnr

How to judge the utility balance of efficient design

Postby xiaojin » Wed Nov 27, 2019 11:09 pm

Dear Ngene expert:
I’m more thankful than I can express for your previous reply.
This is my syntax:
Design
;alts=alt1*,alt2*,alt3
;rows=24
;block=4
;eff=(mnl,d)
;model:
U(alt1)=b1[-0.0016303]*A[100,250,400,550]+b2.effects[0.1388708|0.1552699|0.0522762]*B[3,2,1,0]+b3[0.0003202]*C[1000,2000,3000,4000]+b4[0.0078205]*D[0,20,40,60]+b5.effects[0.2688591]*E[1,0]/
U(alt2)=b1*A+b2*B+b3*C+b4*D+b5*E/
U(alt3)=b0[0]
$

And my questions is:
How to judge the utility balance of efficient design? Is it judged by the value of B-estimate?
So what range of B-estimate can be used to represent utility balance? My B-estimate is 77.748833. Can such a value of B-estimate represent utility balance?

Thank you again!
xiaojin
 
Posts: 20
Joined: Thu Aug 29, 2019 4:55 pm

Re: How to judge the utility balance of efficient design

Postby Michiel Bliemer » Thu Nov 28, 2019 12:17 am

Yes, the B-estimate is a measure of balance. If there is a fully dominant alternative in all choice tasks, then the B-estimate would be 0%, whereas if all alternatives are chosen with equal probabilities then the B-estimate is 100%. Efficient designs (with appropriate non-zero priors) typically have a B-estimate between 70% and 90%.

Michiel
Michiel Bliemer
 
Posts: 1705
Joined: Tue Mar 31, 2009 4:13 pm

Re: How to judge the utility balance of efficient design

Postby xiaojin » Thu Nov 28, 2019 11:24 am

But my B-estimate shows 77.748833 in the Ngene, which is not 77.748833% of the percentage system. Can I directly regard 77.748833 as 77.748833%. So if the value of B-estimate in my experiment is not between 70% and 90%, does that mean I have to redo the design?
xiaojin
 
Posts: 20
Joined: Thu Aug 29, 2019 4:55 pm

Re: How to judge the utility balance of efficient design

Postby xiaojin » Thu Nov 28, 2019 11:30 am

Michiel Bliemer wrote:Yes, the B-estimate is a measure of balance. If there is a fully dominant alternative in all choice tasks, then the B-estimate would be 0%, whereas if all alternatives are chosen with equal probabilities then the B-estimate is 100%. Efficient designs (with appropriate non-zero priors) typically have a B-estimate between 70% and 90%.

Michiel


Dear Michiel:
But my B-estimate shows 77.748833 in the Ngene, which is not 77.748833% of the percentage system. Can I directly regard 77.748833 as 77.748833%. So if the value of B-estimate in my experiment is not between 70% and 90%, does that mean I have to redo the design?
xiaojin
 
Posts: 20
Joined: Thu Aug 29, 2019 4:55 pm

Re: How to judge the utility balance of efficient design

Postby Michiel Bliemer » Thu Nov 28, 2019 5:31 pm

Yes it means 77%, which is fine. It is just a score that Ngene calculates, which ranges from 0 to 100. A design with a B-estimate of 100 is 100% utility balanced.

Michiel
Michiel Bliemer
 
Posts: 1705
Joined: Tue Mar 31, 2009 4:13 pm


Return to Choice experiments - Ngene

Who is online

Users browsing this forum: No registered users and 4 guests

cron