Uncles, Mark; Ehrenberg, Andrew; Hammond, Kathy
June 1995
Marketing Science;1995 Part 2 of 2, Vol. 14 Issue 3, pG71
Academic Journal
In this article, authors list some of the well-established regularities in the buying behavior of consumers and illustrate how this approach to modeling can assist the marketing analyst. Theoretically the Dirichlet model is very parsimonious in its assumptions and input requirements. Not surprisingly, discrepancy problems occur, although they are mostly at the margin. A feature of having a model-a norm-is that any discrepancies stand out. Mostly these are small and explicable in terms of case-specific factors. But where they are systematic a basis exists for further generalization, or even model adaptation. Indeed, it was the widespread occurrence of the DJ "discrepancy" that provided the incentive to develop the Dirichlet as a model of brand choice. The model is about habitual near-steady-state consumer behavior. It is not dynamic. In dynamic situations, however, it provides a useful benchmark. Conditional trend analysis, using the NBD or Dirichlet norms for period-to-period repeat-buying, has enabled studies of the effects of price promotions, seasonality and new product launches, these studies have yielded useful results without having to fine-tune the model itself.


Related Articles

  • Does a Change in Customer Loyalty Occur When a New Car Agency is Sold? Nordstrom, Richard D.; Swan, John E. // Journal of Marketing Research (JMR);May76, Vol. 13 Issue 2, p173 

    Marketing theorists have assumed that changes in market structure variables could affect consumer loyalty behavior. This report presents supportive evidence from an ex post facto experiment showing that a change in a business' ownership was related to significantly altered brand and store...

  • Informal Social Group Influence on Consumer Brand Choice. Witt, Robert E. // Journal of Marketing Research (JMR);Nov69, Vol. 6 Issue 4, p473 

    This article discusses the influence of small, informal social groups on member brand choice. Two determinants of group influence, cohesiveness and group knowledge of member behavior, were found to be significantly related to similarity of brand choice within groups. Variation across products in...

  • Integrating the Dirichlet-Multinomial and Multinomial Logit Models of Brand Choice. Fader, Peter S. // Marketing Letters;Apr93, Vol. 4 Issue 2, p99 

    This paper discusses the interpretative benefits that arise from merging the Dirichlet-multinomial (DM) model as a loyalty variable in the multinomial logit (MNL) model of brand choice. The estimated parameters of this hybrid model compare favorably to those of a "pure" DM model (with no...

  • A Loyalty Group Segmentation Model for Brand Purchasing Simulation. Starr, Martin K.; Rubinson, Joel R. // Journal of Marketing Research (JMR);Aug1978, Vol. 15 Issue 3, p378 

    A model for consumer package goods is described by which consumers can be segmented into loyalty groups. A survey is used to obtain measures of consumer willingness to switch from a regular brand, if there is one. Each loyalty group is associated with a unique purchase probability vector. The...

  • Calculation of Theoretical Brand Performance Measures from the Parameters of the Dirichlet Model. Rungie, Cam; Goodhardt, Gerald // Marketing Bulletin;May2004, Vol. 15, p1 

    The Dirichlet Model is used in marketing to provide a probability density function for the repeated purchases, by shoppers over a period of time, of the competing brands within a product category. The model is used to analyze a range of measures which report on the performance and competitive...

  • Linking Attribute, Benefits, and Consumer Values. Vriens, Marco; Hofstede, Frenkel Ter // Marketing Research;Fall2000, Vol. 12 Issue 3, p4 

    The authors discuss means-end chain analysis as a method to understand why consumers buy certain products or brands. Means-end chain analysis identifies links between product attributes, benefits, and consumer values. This allows marketers to deal with a broad set of marketing problems,...

  • Why Does "Brand Loyalty" Vary Over Products. Farley, John U. // Journal of Marketing Research (JMR);Nov64, Vol. 1 Issue 4, p9 

    This paper tests hypotheses about why measured "brand loyalty" varies over product classes. Factor analysis is used to solve certain difficulties in the empirical testing. Brand switching in a product class appears to be associated with price activity, distribution, characteristics of the supply...

  • Eliminating Consumer Biases in Survey Data by Balanced Tabulation. Benson, Purnell H. // Journal of Marketing Research (JMR);Nov64, Vol. 1 Issue 4, p66 

    Consumers rate brands higher if they are familiar with them. Thus, more widely known brands receive higher ratings in consumer surveys than do less well-known brands that dire superior in qualify. The purpose of this paper is to introduce a procedure to correct data for consumer biases toward...

  • Brand Image and Brand Usage. Bird, M.; Channon, C.; Ehrenberg, A. S. C. // Journal of Marketing Research (JMR);Aug1970, Vol. 7 Issue 3, p307 

    The proportion of people who express an attitude about a given brand generally depends on how recently they have used the brand.


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics