Using data on women’s choice of hospital for childbirth in Florida, we find that women return to the same hospital approximately 70% of the time. We separate explanations of switching costs and unobserved preference heterogeneity using a panel data fixed effects estimator and find that switching costs account for approximately 40% of the demand effects of a lagged dependent variable. The welfare effects of excluding a hospital from a payer’s network are smaller in the short run but higher in the long run, given our estimates of switching costs, and the dynamic effects of entry on competition are significantly smaller.

Satellite-based image classification facilitates low-cost measurement of the Earth’s surface composition. However, misclassified imagery can lead to misleading conclusions about transition processes. We propose a correction for transition rate estimates based on the econometric measurement error literature to extract the signal (truth) from its noisy measurement (satellite-based classifications). No ground-truth data are required in the implementation. Our proposed correction produces consistent estimates of transition rates, confirmed by longitudinal validation data, while transition rates without correction are severely biased. Using our approach, we show how eliminating deforestation in Brazil’s Atlantic forest region through 2040 could save $100 billion in CO2 emissions.