Identification and Estimation of Online Price Competition with an Unknown Number of Firms

This paper considers identification and estimation of a general model for online price competition. We show that when the number of competing firms is unknown, the underlying parameters of the model can still be identified and estimated employing recently developed results on measurement error. With the estimates of model parameters, we are able to analyze the competitive effects of online competition when the number of firms changes. We illustrate our methodology using UK data for personal digital assistants and employ the estimates to simulate competitive effects. Our results reveal that heightened competition has differential effects on the prices paid by different consumer segments.