A NEW CONTINUOUS DEMAND MODEL FOR MARKET LEVEL DATA

This paper considers a new method of uncovering demand information from market level data on dierentiated products. In particular, we propose a continuous- choice demand model with distinct advantages over the models currently in use and describe the econometric techniques for its estimation. The proposed model combines key properties of both the discrete- and continuous-choice traditions: i) it is ‡exible in the sense of Diewert (1974), ii) can deal with the entry and exit of products over time, and iii) incorporates a structural error term. Furthermore, it is relatively simple and fast to estimate which can prove a key advantage in competition policy issues where time and transparency are always crucial factors. Akin also to the continuous-choice tradition, the model encompasses a more general version (not consistent with an indirect utility function) that enables us to test the validity of symmetry properties and, for those cases it appears to be consistent with the data, also impose it a priori. In what concerns the estimation procedure in particular, we propose an analog to the algorithm derived in Berry (1994), Berry, Levinsohn and Pakes (1995). Along the way, we present an alternative procedure to BLP's