Estimating Demand for Differentiated Products: The Case of Beer in the U.S.

This paper employs a nation-wide sample of supermarket scanner data to estimate a large brandlevel demand system for beer in the U.S. Unlike previous studies, this work estimates the ownand cross-advertising elasticities in addition to price elasticities. The dimensionality problem is solved with the Distance Metric method of Pinkse, Slade and Brett and the demand model follows the flexible Almost Ideal demand system. While price elasticities are consistent with previous results, positive and negative cross-advertising elasticities imply the presence of both cooperative and predatory effects of advertising expenditures across brands; however, the former effect appears to dominate suggesting that advertising increases the overall demand for beer.