choice-metrics.com

Hi,

Ngene crashes when the number of alternatives is increased and correspondingly the number of sets reduced even though there are still sufficient degrees of freedom. A similar question was raised in Nov 2018 but there is no update on the forum as to a solution or workaround. Please see example below.

Any help would be much appreciated.

Thank you in advance.

Code: Select all

Design
;alts = A,B
;rows = 16
;eff=(mnl,d)
;model:
U(A) = b1.dummy[0|0|0]*P[1, 2, 3, 4] + b2.dummy[0|0]*C[1, 2, 3] +
i1[0]*P.dummy[1]*C.dummy[1] +
i2[0]*P.dummy[1]*C.dummy[2] +
i3[0]*P.dummy[2]*C.dummy[1] +
i4[0]*P.dummy[2]*C.dummy[2] +
i5[0]*P.dummy[3]*C.dummy[1] +
i6[0]*P.dummy[3]*C.dummy[2] /
U(B) = b1.dummy[0|0|0]*P[1, 2, 3, 4] + b2.dummy[0|0]*C[1, 2, 3] +
i1[0]*P.dummy[1]*C.dummy[1] +
i2[0]*P.dummy[1]*C.dummy[2] +
i3[0]*P.dummy[2]*C.dummy[1] +
i4[0]*P.dummy[2]*C.dummy[2] +
i5[0]*P.dummy[3]*C.dummy[1] +
i6[0]*P.dummy[3]*C.dummy[2] $


Design
;alts = A,B,C
;rows = 8
;eff=(mnl,d)
;model:
U(A) = b1.dummy[0|0|0]*P[1, 2, 3, 4] + b2.dummy[0|0]*C[1, 2, 3] +
i1[0]*P.dummy[1]*C.dummy[1] +
i2[0]*P.dummy[1]*C.dummy[2] +
i3[0]*P.dummy[2]*C.dummy[1] +
i4[0]*P.dummy[2]*C.dummy[2] +
i5[0]*P.dummy[3]*C.dummy[1] +
i6[0]*P.dummy[3]*C.dummy[2] /
U(B) = b1.dummy[0|0|0]*P[1, 2, 3, 4] + b2.dummy[0|0]*C[1, 2, 3] +
i1[0]*P.dummy[1]*C.dummy[1] +
i2[0]*P.dummy[1]*C.dummy[2] +
i3[0]*P.dummy[2]*C.dummy[1] +
i4[0]*P.dummy[2]*C.dummy[2] +
i5[0]*P.dummy[3]*C.dummy[1] +
i6[0]*P.dummy[3]*C.dummy[2] /
U(C) = b1.dummy[0|0|0]*P[1, 2, 3, 4] + b2.dummy[0|0]*C[1, 2, 3] +
i1[0]*P.dummy[1]*C.dummy[1] +
i2[0]*P.dummy[1]*C.dummy[2] +
i3[0]*P.dummy[2]*C.dummy[1] +
i4[0]*P.dummy[2]*C.dummy[2] +
i5[0]*P.dummy[3]*C.dummy[1] +
i6[0]*P.dummy[3]*C.dummy[2] $


Both syntax run fine for me. Can you please confirm that you have the latest version of Ngene installed? If you have, could you please share the syntax with which Ngene crashes?

Michiel

Hi Michiel

Rookie mistake. Indeed it runs fine on the updated version, many thanks.

Manos