T. Erdem et Mp. Keane, DECISION-MAKING UNDER UNCERTAINTY - CAPTURING DYNAMIC BRAND CHOICE PROCESSES IN TURBULENT CONSUMER-GOODS MARKETS, Marketing science, 15(1), 1996, pp. 1-20
We construct two models of the behavior of consumers in an environment
where there is uncertainty about brand attributes. In our models, bot
h usage experience and advertising exposure give consumers noisy signa
ls about brand attributes. Consumers use these signals to update their
expectations of brand attributes in a Bayesian manner. The two models
are (1) a dynamic model with immediate utility maximization, and (2)
a dynamic ''forward-looking'' model in which consumers maximize the ex
pected present value of utility over a planning horizon. Given this th
eoretical framework, we derive from the Bayesian learning framework ho
w brand choice probabilities depend on past usage experience and adver
tising exposures. We then form likelihood functions for the models and
estimate them on Nielsen scanner data for detergent. We find that the
functional forms for experience and advertising effects that we deriv
e from the Bayesian learning framework fit the data very well relative
to flexible ad hoc functional forms such as exponential smoothing, an
d also perform better at out-of-sample prediction. Another finding is
that in the context of consumer learning of product attributes, althou
gh the forward-looking model fits the data statistically better at con
ventional significance levels, both models produce similar parameter e
stimates and policy implications. Our estimates indicate that consumer
s are risk-averse with respect to variation in brand attributes, which
discourages them from buying unfamiliar brands. Using the estimated b
ehavioral models, we perform various scenario evaluations to find how
changes in marketing strategy affect brand choice both in the short an
d long run. A key finding obtained from the policy experiments is that
advertising intensity has only weak short run effects, but a strong c
umulative effect in the long Nn. The substantive content of the paper
is potentially of interest to academics in marketing, economics and de
cision sciences, as well as product managers, marketing research manag
ers and analysts interested in studying the effectiveness of marketing
mix strategies. Our paper will be of particular interest to those int
erested in the long run effects of advertising. Note that our estimati
on strategy requires us to specify explicit behavioral models of consu
mer choice behavior, derive the implied relationships among choice pro
babilities, past purchases and marketing mix variables, and then estim
ate the behavioral parameters of each model. Such an estimation strate
gy is referred to as ''structural'' estimation, and econometric models
that are based explicitly on the consumer's maximization problem and
whose parameters are parameters of the consumers' utility functions or
of their constraints are referred to as ''structural'' models. A key
benefit of the structural approach is its potential usefulness for pol
icy evaluation. The parameters of structural models are invariant to p
olicy, that is, they do not change due to a change in the policy. In c
ontrast, the parameters of reduced form brand choice models are, in ge
neral, functions of marketing strategy variables (e.g., consumer respo
nse to price may depend on pricing policy). As a result, the predictio
ns of reduced form models for the outcomes of policy experiments may b
e unreliable, because in making the prediction one must assume that th
e model parameters are unaffected by the policy change. Since the agen
ts in our models choose among many alternative brands, their choice pr
obabilities take the form of higher-order integrals. We employ Monte-C
arlo methods to approximate these integrals and estimate our models us
ing simulated maximum likelihood. Estimation of the dynamic forward-lo
oking model also requires that a dynamic programming problem be solved
in order to form the likelihood function. For this we use a new appro
ximation method based on simulation and interpolation techniques. Thes
e estimation techniques may be of interest to researchers and policy m
akers in many fields where dynamic choice among discrete alternatives
is important, such as marketing, decision sciences, labor and health e
conomics, and industrial organization.