Estimating baysian priors from a pilot study

This forum is for posts that specifically focus on Ngene.

Moderators: Andrew Collins, Michiel Bliemer, johnr

Re: Estimating baysian priors from a pilot study

Postby TamsinD » Fri May 03, 2024 8:40 pm

Thank-you so much for your help with estimating the priors. Your explanations have been really clear and helped me understand it better.
My modified syntax for Ngene is now as follows, so will use this for the survey distribution. Sample size is 242.
Thanks again.

design
;alts = opt1, opt2
? efficient design
;eff = (mnl, d, median)
;rows = 36
;bdraws = sobol(1000)

;model:
U(opt1) = b1.dummy[(n,0.485,0.129)|(n,0.199,0.116)|(n,-0.006,0.111)] * x1[0,1,2,3]
+ b2[(n,-0.013,0.006)] * x2[30,40,50]
+ b3[(n,-0.041,0.0014)] * x3[10,20]
+ b4[(n,-0.013,0.006)] * x4[2,5,10]
+ b5[(n,-0.095,0.030)] * x5[2,3,4,5,6]
+ b6.dummy[(n,0.171,0.044)] * x7[0,1]
+ asc1[(n,-0.201,0.546)]
/
U(opt2) = b7[(n,-0.022,0.011)] * x2_2[30,35,40]
+ b8[(n,-0.039,0.047)] * x5_2[1,2,3,4,5]
+ b9[(n,-0.070,0.009)] * x6_2[0,5,10,15]
+ b6 * x7
$
TamsinD
 
Posts: 10
Joined: Tue Apr 23, 2024 9:00 pm

Previous

Return to Choice experiments - Ngene

Who is online

Users browsing this forum: No registered users and 13 guests