Uij = u (yj, Zj, εij)
where i is the dichotomous choice (1 as the preferred state and 0 the status quo) and j refers to
respondent. The determinants of utility are yj, the jth respondent’s income, Zj, a vector of
respondent characteristics and attributes of the choice, and εij, a component of preferences known
to the individual respondent but not observed by the researcher.
(1)
Based on this model, respondent j chooses the non-GM food if the utility of non-GM
food exceeds the utility of the status quo (GM food), given prices:
Uij(Zj, yj - Pngmj,1, εij) > Uoj (Zj, yj — Pgmj, 0, sj (2)
where 1 denotes the respondent j choosing the non-GM food, 0 denotes the respondent j
choosing the status quo (GM food), Pngmj is the price of non-GM food, Pgmj is the price of GM
food. All other variables were defined previously.
Therefore, the probability that the respondent thinks he/she is better off by choosing the
non-GM food, given its price can be expressed as:
Prob (Respondent j chooses non-GM food)
= Prob [Uij(Zj, yj — Pngmj,1, ɛɪj) > Uoj (Zj, yj — Pgmj,0, ɛoj)] (3)
The Logistic Model
With a further assumption of the linear form for the utility function, the utility of
respondent j choosing the non-GM food can be specified as:
U1j = α1Zj + β1 (Yj - Pngmj) + ε1j (4)
And the utility of respondent j choosing the GM food is:
U0j = α0Zj + β0 (Yj - Pgmj) + ε0j (5)