Demand Estimation with Differentiated Products: An Application to Price Competition in the U.S. Brewing Industry

A large part of the empirical work on differentiated products markets has focused ondemand estimation and the pricing behavior of firms. These two themes are key inputsin important applications such as the merging of two firms or the introduction of newproducts. The validity of inferences, therefore, depends on accurate demand estimatesand sound assumptions about the pricing behavior of firms. This dissertation makesa contribution to this literature in two ways. First, it adds to previous techniques ofestimating demand for differentiated products. Second, it extends previous analyses ofpricing behavior to models of price leadership that, while important, have received limitedattention. The investigation focuses on the U.S. brewing industry, where price leadershipappears to be an important type of firm behavior.The analysis is conducted in two stages. In the first stage, the recent Distance Metric(DM) method devised by Pinkse, Slade and Brett is used to estimate the demand for 64brands of beer in 58 major metropolitan areas of the United States. This study adds toprevious applications of the DM method (Pinkse and Slade; Slade 2004) by employing ademand specification that is more flexible and also by estimating advertising substitutioncoefficients for numerous beer brands.In the second stage, different pricing models are compared and ranked by exploitingthe exogenous change in the federal excise tax of 1991. Demand estimates of the firststage are used to compute the implied marginal costs for the different models of pricingbehavior prior to the tax increase. Then, the tax increase is added to the these pre-taxincrease marginal costs, and equilibrium prices for all brands are simulated for each modelof pricing behavior. These "predicted" prices are then compared to actual prices for modelassessment.Results indicate that Bertrand-Nash predicts the pricing behavior of firms more closelythan other models, although Stackelberg leadership yields results that are not substanitallydifferent from the Bertrand-Nash model. Nevertheless, Bertrand-Nash tends tounder-predict prices of more price-elastic brands and to over-predict prices of less price-elastic brands. An implication of this result is that Anheuser-Busch could exert moremarket power by increasing the price of its highly inelastic brands, especially Budweiser.Overall, actual price movements as a result of the tax increase tend to be more similaracross brands than predicted by any of the models considered. While this pattern is notinconsistent with leadership behavior, leadership models considered in this dissertationdo not conform with this pattern.