.png){kind=icon}
.png){kind=icon}
Return
Reverse discrete choice models
.png){kind=icon}
PRE
AI
DOI：10.1016/S0166-0462(99)00009-5.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
We derive the cost minimization counterpart to the usual utility maximization version of the multinomial logit (MNL) model. Equivalently, our model considers the reverse of the usual error structure in the maximization problem. The resulting model remains tractable but does not suffer from the IIA property of the MNL. Our technique also provides a variant on the standard CES model (that does not exhibit IIA either). We argue that these models are useful alternatives to the standard ones, and compare their predictions for firm pricing. We also discuss the properties of other reverse models. (C) 1999 Elsevier Science B.V. All rights reserved. JEL classification: L13; C25; R19.
Keywords:
CES
discrete choice
error structure
IIA
logit
minimization problem
Journal
IF:
2.9
Papers:
2.3K
Citations:
4.8K
Organization
No organization information available