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...

The logit model is the most popular tool for estimating demand in differentiated products markets. However, in its aggregate version, practitioners have to “guess” the size outside good. We propose a way to remove the bias created by an inaccurate guess in simpler versions of the model.

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...