Search with Learning for Differentiated Products: Evidence from E-Commerce

(Dr. Babur De Los Santos with Ali Hortaçsu and Matthijs R. Wildenbeest, Journal of Business & Economic Statistics, forthcoming)

 

This paper provides a method to estimate search costs in a differentiated product environment in which consumers are uncertain about the utility distribution. Consumers learn about the utility distribution by Bayesian updating their Dirichlet process prior beliefs. The model provides expressions for bounds on the search costs that can rationalize observed search and purchasing behavior. Using individual-specific data on web browsing and purchasing behavior for MP3 players sold online we show how to use these bounds to estimate search costs as well as the parameters of the utility distribution. Our estimates indicate that search costs are sizable. We show that ignoring consumer learning while searching can lead to severely biased search cost and elasticity estimates.

 

Download This Paper

Related posts:

Read previous post:
Vernon-Smith
Renowned economist, Nobel winner Vernon Smith spoke at Clemson October 5

October 5, 2015 Distinguished economist and 2002 Nobel Prize winner Vernon L. Smith spoke at Clemson University today as part of...

Close