The video entertainment industry is experiencing increases in over-the-top (OTT) video usage and cord-cutting behavior. Using unique panel data from 2012–2016, we document the behavior of the 2.4% of households who “cut the cord” annually. After dropping TV, these households increase internet usage by 22%, reduce payments to multiple-system operators (MSOs) by 50%, and 16% acquire new OTT video subscriptions. These results indicate meaningful substitution between OTT video and TV and suggest that competition authorities should consider broadening market definitions. MSOs appear to have little incentive to degrade OTT video, despite OTT video's contribution to declining TV revenues.

Dealing with endogenous regressors is a central challenge of applied research. The standard solution is to use instrumental variables that are assumed to be uncorrelated with unobservables. We instead allow the instrumental variable to be correlated with the error term, but we assume the correlation between the instrumental variable and the error term has the same sign as the correlation between the endogenous regressor and the error term and that the instrumental variable is less correlated with the error term than is the endogenous regressor. Using these assumptions, we derive analytic bounds for the parameters. We demonstrate that the method can generate useful (set) estimates by using it to estimate demand for differentiated products.

This paper examines the construction of a price index based on an estimated-demand system. In principle the method examined can produce a price index that takes account of the introduction of new products and quality changes in existing products. However, I isolate two key assumptions that have to be made in order to interpret the demand estimates into welfare measures. Using estimates of a brand-level demand system for ready-to-eat cereal, I demonstrate the empirical importance of the assumptions. For the data I use, depending on the interpretation of the demand estimates, a price index can range between a 35% increase over the five years examined to a 2.4% decrease.