USING ORDER STATISTICS TO ESTIMATE PROBABILITIES OF PURCHASE FOR CONSUMER GOODS

Abstract

Much work has been done recently to develop models of individual brand choice. This work has been especially fruitful in the area of “attribute investigation” (e.g., conjoint analysis) for the purpose of uncovering an “ideal” set of product attributes for a given product on a customer-by-customer basis. These techniques have been employed in several strategic areas of marketing, including product specification, pricing, service prioritization, brand image/equity, and satisfaction/loyalty. Similarly, some effort has been made with the issue of optimal advertising strategy. This paper considers the advertising effectiveness function within the context of other interrelated variables such as consumer preference (brand choice) for a brand vis-à-vis its competitors. The model suggests, among other things, that under certain reasonable conditions, the advertising response function may not be “diminishing marginal returns” or ‘S-shaped’ as is usually assumed, but instead will increase up to a point and then decline. The model also explicitly considers the advertising expenditures of competing brands, as well as intrinsic "liking" for them. The consideration of competitive activity, in the present study may yield a more complete model of advertising response than is found elsewhere. Finally the model provides direction for strategic purposes in its ability to illustrate in a fairly straightforward and graphical sense how advertising and promotion “work” in much the same way that demand and supply curves illustrate how the various economic inputs work.