Both the recent advances in econometric analysis of panel data in economics
and the availability of scanner panel data in marketing have motivated mar
keting researchers to conduct internal analysis of market structure based o
n revealed preference data. This kind of analysis allows the analyst to inf
er brand positions in an attribute space from preference and choice data, g
iven a market in which consumers have heterogeneous tastes for attributes.
Extant market structure models based on disaggregate panel data are probabi
listic models that provide spatial representations of market structure but
if a few products share the same brand name across product categories, cons
umer perceptions of product locations sharing the same brand name may be in
terdependent. The main contribution of this paper is to present a probabili
stic spatial panel data model that allows the positions of products sharing
the same name to be correlated across product categories. (C) 1999 Elsevie
r Science S.A. All rights reserved. JEL classification. C23; C25; M31.