Coverage of retail stores and discrete choice models of demand : estimating price elasticities and welfare effects

Consumers' choice set of products within stores can be limited. Ackerberg and Rysman (2005) address this problem by modeling unobserved consumer preferences over products and retail stores, leading to augmented demand specifications. Having Carbonated Soft Drink product level data, where we observe products' store coverage, we are able to estimate their logit, nested logit and random coefficient logit specifications of demand in a structural model of equilibrium. Allowing for store coverage turns out to have a very significant impact on the estimated structural parameters and on the predictive power of the model. Taking these estimated structural parameters we perform a counterfactual whereby stores carry all products in the market. We find systematic increases in price elasticities and welfare in our new equilibrium. Competition in markets is more curtailed than normally assumed in structural models of industries.