choice-metrics.com

Dear Ngene experts:
I am relatively new to Ngene. In the design of DCE, I encountered some questions. I want to find the answers in the forum. If I can get your help, I would appreciate it very much.
This is my syntax:
Design
;alts=alt1*,alt2*,alt3
;rows=12
;block=6
;eff=(mnl,d)
;model:
U(alt1)=b1.effects[0.001]*A[0,1]+b2.effects[0.002|0.001]*B[0,1,2]+b3.effects[0.003|0.002|0.001]*C[0,1,2,3]+b4.effects[0.002|0.001]*D[0,1,2]+ b5.effects[-0.002|-0.001]*E[0,1,2]/
U(alt2)=b1*A+b2*B+b3*C+b4*D+b5*E/
U(alt3)=b0[0]
$

First, I have two questions about the formatting experiments:
1 As shown above, my syntax is “rows=12, block=2”.I added block to my syntax, but it didn’t shown up in the final display, it only shows consecutive scenarios 1 to 12. Should I automatically use scenario 1 to 6 as the first block and scenario 7 to 12 as the second block?

2 In final display, ”no choice alternatives(alt3)” are also not shown. Do I need to add it manually in “configure scenario formatting”?

Then there are some details.
3 As shown above, the number of my attribute levels is 2,3,4. And I set “rows=12, block=2”. So I have 6 in each block, but 6 is not divisible by 2,3,4. And my question is “Is it ok for attribute level imbalance within each block?

4 For example, the variable C in the syntax represents the “payment ceiling”. Because level 3 is the base. So 3 stands for 1000 yuan, and 2 for 2000, 1 for 3000, 0 for 4000. But it’s a little awkward. So I’d like to ask, is it feasible to change the order of all attribute levels from 0,1,2,3 to 3,2,1,0? Then 0 stands for 1000 yuan, 1 for 2000, 2 for 3000,3 for 4000. As shown below:

Design
;alts=alt1*,alt2*,alt3
;rows=12
;block=6
;eff=(mnl,d)
;model:
U(alt1)=b1.effects[0.001]*A[1,0]+b2.effects[0.002|0.001]*B[2,1,0]+b3.effects[0.003|0.002|0.001]*C[3,2,1,0]+b4.effects[0.002|0.001]*D[2,1,0]+ b5.effects[-0.002|-0.001]*E[2,1,0]/
U(alt2)=b1*A+b2*B+b3*C+b4*D+b5*E/
U(alt3)=b0[0]
$

If my question seems very ignorant, please forgive me. Thank you again for your help

1. The block numbers are in the design when you open the design in the output window. In the survey instrument that you implement your survey in, you have to group the choice tasks within each block manually. You can show the blocks in the formatting in Ngene by editing the title when you configure the scenario formatting (there is a button at the top with the name "Block number"). Note that currently you have block = 6, not block =2. See the syntax below.

2. Yes you need to manually add this column, which has no attributes. See the syntax below.

This syntax has formatting that shows the optout alternative and also the block number in the scenario title:

Design
;alts=alt1*,alt2*,alt3
;rows=12
;block=6
;eff=(mnl,d)
;model:
U(alt1)=b1.effects[0.001]*A[0,1]+b2.effects[0.002|0.001]*B[0,1,2]+b3.effects[0.003|0.002|0.001]*C[0,1,2,3]+b4.effects[0.002|0.001]*D[0,1,2]+ b5.effects[-0.002|-0.001]*E[0,1,2]/
U(alt2)=b1*A+b2*B+b3*C+b4*D+b5*E/
U(alt3)=b0[0]
;formatTitle = 'Scenario <scenarionumber> in block <blocknumber>'
;formatTableDimensions = 4, 7
;formatChoices = choice
;formatTable:
1,1 = '' /
1,2 = 'a' /
1,3 = 'b' /
1,4 = 'c' /
1,5 = 'd' /
1,6 = 'e' /
1,7 = 'Choice question&:' /
2,1 = 'alt1' /
2,2 = '<alt1.a>' /
2,3 = '<alt1.b>' /
2,4 = '<alt1.c>' /
2,5 = '<alt1.d>' /
2,6 = '<alt1.e>' /
2,7 = '<choice>' /
3,1 = 'alt2' /
3,2 = '<alt2.a>' /
3,3 = '<alt2.b>' /
3,4 = '<alt2.c>' /
3,5 = '<alt2.d>' /
3,6 = '<alt2.e>' /
3,7 = '<choice>' /
4,1 = 'Neither' /
4,2 = '' /
4,3 = '' /
4,4 = '' /
4,5 = '' /
4,6 = '' /
4,7 = '<choice>'
;formatTableStyle:
1,1 = 'default' /
1,2 = 'headingattribute' /
1,3 = 'headingattribute' /
1,4 = 'headingattribute' /
1,5 = 'headingattribute' /
1,6 = 'headingattribute' /
1,7 = 'headingattribute' /
2,1 = 'heading1' /
2,2 = 'body1' /
2,3 = 'body1' /
2,4 = 'body1' /
2,5 = 'body1' /
2,6 = 'body1' /
2,7 = 'choice1' /
3,1 = 'heading2' /
3,2 = 'body2' /
3,3 = 'body2' /
3,4 = 'body2' /
3,5 = 'body2' /
3,6 = 'body2' /
3,7 = 'choice2' /
4,1 = 'heading3' /
4,2 = 'body3' /
4,3 = 'body3' /
4,4 = 'body3' /
4,5 = 'body3' /
4,6 = 'body3' /
4,7 = 'choice3'
;formatStyleSheet = Blue buttons.css
;formatAttributes:
alt1.a(0=#, 1=#) /
alt1.b(0=#, 1=#, 2=#) /
alt1.c(0=#, 1=#, 2=#, 3=#) /
alt1.d(0=#, 1=#, 2=#) /
alt1.e(0=#, 1=#, 2=#) /
alt2.a(0=#, 1=#) /
alt2.b(0=#, 1=#, 2=#) /
alt2.c(0=#, 1=#, 2=#, 3=#) /
alt2.d(0=#, 1=#, 2=#) /
alt2.e(0=#, 1=#, 2=#)
$

3. That is not a problem. What is more problematic is that you only have 12 choice tasks for estimating 13 parameters. I would suggest increasing the number of choice tasks to 24 to increase variety in your data.

4. Yes that is perfectly fine, you can change the order to anything you like (of course the priors need to be consistent with this ordering).

Michiel