2013): “Estimating Demand in Search Markets: the Case of Online Hotel Bookings

In this paper, we emphasize that choice sets generated by search process have two properties: \u85 rst, they are limited; second, they are endogenous to preferences. Both factors lead to biased estimates in a static demand framework that takes choice sets as given. To correct for this bias, we estimate a structural model of search for di¤erentiated products, using a unique dataset of consumer online search for hotels. Within nested logit utility model, we show that the mean utility function and the search cost distribution of a representative consumer are non-parametrically identi\u85ed, given our data. Using our models estimates, we quantify both sources of bias: they lead to over-estimation of price elasticity by \u85ve and four times respectively. The median search cost is about 38 dollars per 15 hotels; we also present some evidence on multi-modality of search cost distribution