Page 1 of 1

Consequences of changing the values of continious variable

PostPosted: Wed Jan 31, 2024 7:45 pm
by dce.farmers
Dear Ngene users,

My efficient design is now (almost) ready for pilot test although I have to change the levels' value of my continious variable in the following way:

Cost attribute --> 4 levels (40000 €,44000 €,48000 €,52000€), continious variable

to

Cost attribute --> 4 levels (45000 €,50000 €,55000 €,60000€), continious variable

Do I need to run my code again in Ngene (with the updated values) and select a new efficient design or can I just update the design I have previously selected such that I only change the values in the following way: 40000 becomes 45000, 44 000 becomes 50000, 48000 becomes 55000 and 52000 becomes 60000? I would be willing to do the second option instead as I have already tested my choice cards so I do not wish to change how the cards look like but simply update the values. I do not know however if this change of values affects other parameters of the model and if it is best to start all over again.

I am attaching my current Ngene code below:

Code: Select all
design
;alts = alt1*, alt2*, alt3
;rows = 24
;eff = (mnl,d)
;block = 4
;alg = mfederov
;reject:
alt2.cost=52000 and alt2.plantation=2,
alt2.cost=52000 and alt2.plantation=3,
alt1.cost=52000 and alt1.plantation=2,
alt1.cost=52000 and alt1.plantation=3,
alt2.cost=40000 and alt2.plantation=1,
alt1.cost=40000 and alt1.plantation=1
;model:
U(alt1)= b1.dummy[0.00001|0.00002]*support[2,3,1]                      + b2.dummy[0.0001|0.0001]*plantation[2,3,1]                       + b3[-0.00001]*cost[40000,44000,48000,52000](5-7,5-7,5-7,5-7)
                     + b4.dummy[0.0001|0.0001]*spraying[2,3,1]
                     + b5.dummy[0.00002]*suivi[1,2]   
                     + b6[0.00001]*cost*plantation /
U(alt2)= b1*support
         + b2*plantation
         + b3*cost
         + b4*spraying
         + b5*suivi
         + b6*cost*plantation /

U(alt3)= b0[0]
$


Thank you in advance for the help!*
Best,
Gaëlle

Re: Consequences of changing the values of continious variab

PostPosted: Thu Feb 01, 2024 8:44 am
by Michiel Bliemer
You can just relabel the levels as you indicate, the difference in efficiency is negligible since you used noninformative (near-zero) priors.

Michiel