The authors investigate the changing role of marketing communication over the life cycle of a new product category. They postulate two effects of marketing communication on consumers' choices: an “indirect effect” through reduction of uncertainty about product quality and a “direct effect” (i.e., more is better). The authors expect that the indirect effect is relatively larger in the early, postlaunch stages. They develop a structural model of demand that allows for such temporal differences in the roles of marketing communication. They use a random coefficients discrete choice model with a Bayesian learning process to model physician learning about new drugs and market-level data for the prescription antihistamines category. They find that marketing communication has a primarily indirect effect 6–14 months after introduction but that the direct effect subsequently dominates. The results suggest that firms should follow a pattern of heavier communication at the introduction phase followed by lower levels.
Improving the Performance of Random Coefficients Demand Models: The Role of Optimal Instruments
