choice-metrics.com

Dear Prof. Bliemer,
I have two experimental designs; the first is 12 rows, and the second is 24 rows with two blocks. The D-error are 0.463929 and 0.211155, respectively. I have determined 30 participants for the pilot study. The syntax for the first is

Code: Select all

Design
;alts=alt1*,alt2*,alt3
;rows=12
;eff=(mnl,d)
; con
;model:
U(alt1)=b0[0.001]+b1.dummy [0.0004|0.0003|0.0002|0.0001|0.0001] * locate[5,4,3,2,1,0]+b2.dummy[0.0002|0.0001|0.0001] * pretest[3,2,1,0]+b3.dummy [0.0002|0.0001|0.0001] * posttest[3,2,1,0]+b4.dummy[-0.0002] *anonym [1,0]+ b5.dummy[0.0002] *method[1,0]+b6[-.0003]*price[0,100,300,700]/
U(alt2)=b0+b1*locate+b2* pretest+b3* posttest+b4*anonym+ b5.dummy *method+b6*price
$


What is the design I will choose?
Sincerely your,
Sukunta

I would use 24 rows with 2 blocks since you have a large number of coefficients to estimate. Using 12 rows is possible but it is quite minimal. There is no harm in using a larger number of rows.

Dear Prof.Bliemer,
Thank you so much for your recommendation. Must the participant be twice as 30? I have limitations regarding the sample size of the pilot study.
Sincerely yours,
Sukunta

A pilot study is typically conducted with 10% of the envisaged final sample.

Dear Prof. Bliemer,
Thank you so much for your recommendation.
Sincerely yours,
Sukunta