Premium
The flexible coefficient multinomial logit (FC‐MNL) model of demand for differentiated products
Author(s) -
Davis Peter,
Schiraldi Pasquale
Publication year - 2014
Publication title -
the rand journal of economics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 3.687
H-Index - 108
eISSN - 1756-2171
pISSN - 0741-6261
DOI - 10.1111/1756-2171.12041
Subject(s) - multinomial logistic regression , discrete choice , econometrics , multinomial probit , probit , mixed logit , logit , monte carlo method , multivariate statistics , class (philosophy) , multinomial distribution , contrast (vision) , generalized extreme value distribution , mathematics , extreme value theory , computer science , mathematical optimization , logistic regression , statistics , artificial intelligence
We show FC‐MNL is flexible in the sense of Diewert ([Diewert, E., 1974]), thus its parameters can be chosen to match a well‐defined class of possible own‐ and cross‐price elasticities of demand. In contrast to models such as Probit and Random Coefficient‐MNL models, FC‐MNL does not require estimation via simulation; it is fully analytic. Under well‐defined and testable parameter restrictions, FC‐MNL is shown to be an unexplored member of McFadden's class of Multivariate Extreme Value discrete‐choice models. Therefore, FC‐MNL is fully consistent with an underlying structural model of heterogeneous, utility‐maximizing consumers. We provide a Monte‐Carlo study to establish its properties and we illustrate its use by estimating the demand for new automobiles in Italy.