Statistical modeling of repeat buying and brand loyalty

Abstract

Relationship marketing concept has been getting much attention from the marketing literature. Empirically, the effectiveness of relationship marketing efforts could be reflected in terms of brand loyalty. Accordingly, marketers have paid growing attention to measure and quantify their brand loyalty. This dissertation develops LSD regression model, reparameterizes NBD regression model and formularizes extended dirichlet regression model. The guiding philosophy is that such models allow for more behaviorally realistic representations of customer buying process, and consequently better understand of brand loyalty. Empirical examples are given in support of our approaches. We show that our proposed models can deliver high performance in terms of model fit and predictive power. Moreover, the dissertation provides the business practitioners with practical suggestions and references in their attempt to enhance relationship marketing.

Date of Award	15 Jul 2008
Original language	English
Awarding Institution	City University of Hong Kong
Supervisor	Hing Po LO (Supervisor)