Abstract

The Negative Binomial-Dirichlet Model of brand choice and purchase incidence has been found to be capable of describing consumer behaviour in a large number of empirical applications. However, a major drawback of this model is the postulate of stationary market conditions. The multivariate Polya Model generalizes this approach in order to overcome the before-mentioned shortcoming. The present paper proposes a further extension: the incorporation of consumer-specific variables. This Extended Polya Model is thus suited to describe dynamic changes at the micro level of individual buyers. Amongst others a useful feature of the Extended Polya Model is its capability to account for asymmetries between brands. It is shown that the multivariate Negative Binomial Distribution Model and the Polya Model with homogeneous explanatory variables are nested within this model. This way the market analyst is provided with a general and flexible approach that allows the modelling of consumer behaviour with various degrees of complexity. The models are applied to empirical data concerning the introduction of a new brand in the German detergent market, and the results obtained are compared with regard to descriptive power and computational effort. It is found that the buyers of the new brand are more price sensitive (assessed in terms of direct and cross elasticities) than consumers of the well-established brands.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call