Estimating Demand with Multi-Homing in Two-Sided Markets

Abstract

We empirically investigate the impact of multi-homing in two-sided markets. First, we build a micro-founded structural econometric model, which encompasses demand for differentiated products and allows for multi-homing on both sides of the market. We then use an original dataset on the Italian daily newspaper market that includes information on readership duplication to estimate readers' and advertisers' demand. The results show that an econometric model that does not allow for multi-homing is likely to produce biased estimates of own- and cross-price elasticities on both sides of the market. On the reader side of the market, accounting for multi-homing allows products to be complements. On the advertising side, our findings suggest that advertising demand depends not only on the readership size, but also on the share of exclusive readers, therefore emphasizing the importance of taking into account readership composition in the demand estimation. (with Pauline Affeldt and Lapo Filistrucchi)