Market basket choice is a decision process in which a consumer selects item
s from a number of product categories on the same shopping trip. The key fe
ature of market basket choice is the interdependence in demand relationship
s across the items in the final basket. This research develops a new approa
ch to the specification of market basket models that allows a choice model
for a basket of goods to be constructed using a set of "local" conditional
choice models corresponding to each item in the basket. The approach yields
a parsimonious market basket model that allows for any type of demand rela
tionship across product categories (complementarity, independence, or subst
itution) and can be estimated using simple modifications of standard multin
omial logit software. We analyze the choice of four grocery store categorie
s that exhibit common cross-category brand names for both national brands a
nd private labels. Results indicate that cross-category price elasticities
are small. We argue that store traffic patterns may be more important than
consumer-level demand interdependence in forecasting market basket choice.