Varying parameter models to accommodate dynamic promotion effects

The purpose of this paper is to examine the dynamic effects of sales promotions. We create dynamic brand sales models (for weekly store-level scanner data) by relating store intercepts and a brand's own price elasticity to a measure of the cumulated previous price discounts – amount and time – for that brand as well as for other brands. The brand's own non-price promotional response parameters are related to the time since the most recent promotion for that brand as well as for other brands. We demonstrate that these dynamic econometric models provide greater managerial relevance than static models can.