Zero s-estimate

This forum is for posts that specifically focus on Ngene.

Moderators: Andrew Collins, Michiel Bliemer, johnr

Zero s-estimate

Postby jane5555 » Wed Sep 14, 2022 4:03 pm

I've developed an orthogonal design for an unlabelled experiment, however the results show an S-estimate of zero. How do I resolve this?

Design
; alts = optionA* , optionB* , optionC* , optionD*
; rows = 16
; block = 4
; orth = seq
; model:
U( optionA ) = btraveltime * tt[1,2,15,26] +
bfare * fare[1865,1900,860,690] +
bdelay * delay [3,6,44,78] +
bdirect.dummy * direct [0,1] +
bwifi.dummy * wifi [0,1] /
U( optionB ) = btraveltime * tt + bfare * fare +
bdelay * delay + bdirect * direct + bwifi.dummy * wifi /

U( optionC ) = btraveltime * tt + bfare * fare +
bdelay * delay + bdirect * direct + bwifi.dummy * wifi /

U( optionD ) = btraveltime * tt + bfare * fare +
bdelay * delay + bdirect * direct + bwifi.dummy * wifi
$
jane5555
 
Posts: 7
Joined: Tue Sep 13, 2022 8:41 am

Re: Zero s-estimate

Postby Michiel Bliemer » Wed Sep 14, 2022 9:22 pm

Sample size estimates can only be calculated if non-zero priors are specified. Your priors are all equal to zero. Note that sample size estimates are only meaningful if prior parameter values are reasonably reliable.

For more information about the calculation of sample size estimates:
Rose, J.M. and M.C.J. Bliemer (2013) Sample size requirements for stated choice experiments. Transportation, Vol. 40, No. 5, pp. 1021-1041.

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

Re: Zero s-estimate

Postby jane5555 » Thu Sep 15, 2022 6:52 am

Thank you
jane5555
 
Posts: 7
Joined: Tue Sep 13, 2022 8:41 am


Return to Choice experiments - Ngene

Who is online

Users browsing this forum: Google [Bot] and 6 guests

cron