When Pavarotti Meets Harry Potter at the Super Bowl

Abstract

This study aims to assess the magnitude of the interdependencies across leisure activities. Such interdependencies can be due not only to the time and budget constraints, but also to correlation in preferences across these activities as well as the need to pay travel costs for out-of-home activities.To capture these effects we introduce a multiple discrete-continuous choice model in which consumers have heterogeneous preferences over a latent attribute space and pricing is non-linear. The combination of multiple discrete-continuous choice with non-linear pricing makes the estimation challenging. We overcome this obstacle by using a powerful genetic algorithm in the estimation.Using structural estimation and individual level data on the allocation of time of Americans in 2003 we find that there are significant interdependencies across leisure activities and that travel costs as well as correlated preferences play an important role in creating them.These interdependencies have important implications to various strategic decisions such as pricing, bundling and mergers.