University:
Boston University
Course:
CAS EC 203 | Empirical Economics 1
Academic year:

2024
Views:

421

Pages:

1
Author:

sakurasparrow51xu

Price Competition with Endogenous Entry: The Effects of Marriott & Starwood’s Merger in Texas (Job Market Paper) This paper quantifies the social welfare effects of Marriott's acquisition of Starwood in Texas. Using a price competition model with endogenous entry, I simulate pre- and post-merger equilibrium market outcomes. I use moment inequality estimation to avoid any arbitrary equilibrium selection mechanism, and propose a novel dominant strategy equilibrium lower bound to reduce the intimidating computation burden from having many players. Results imply a fairly competitive industry, where the price elasticity is between [-15.12, -11.21]. Comparing the pre- and post-merger scenarios, I show that the merger is beneficial for consumers. In markets that are currently being served, the merger increases consumer surplus by 17.14%-24.03%; while in potential markets, 6%-24% of them will have either Marriott or Starwood entered after the merger. Notably, I find that when the entry stage is overlooked, the biases in cost synergy effect and the neglect of entry into new markets would oppositely determine a harmful merger. Payment Instrument Choice with Scanner Data: An MM algorithm for Fixed Effects in Non-linear Models Over the past several decades, the US payments system has shifted from paper payment instruments, namely cash and check, to digital instruments, such as debit cards and credit cards. This paper studies the determinants of this payment choice transition over short and long horizons. Using transaction level panel data, we estimate a multinomial logit discrete choice model with household-choice-quarter fixed effects. We develop a new method based on the Minorization-Maximization (MM) algorithm to address the prohibitive computational challenge of estimating over 1 million fixed effects in a nonlinear model. Results show that over a short horizon (within a quarter), the probability of using card increases with transaction sizes. While over long horizon (five-year period of the data), aggregate value-weighted card usage increases by 9.73 percentage points. With the estimated quarterly household-choice fixed effects, we decompose such an increase into different channels and find that only a third of it is due to the changes in household preferences. Spatial Competition and Missing Data: an Application to Cloud Computing The internet was hypothesized to be the “death of distance”. We investigate this hypothesis with a novel anonymized customer level dataset on demand for cloud computing accounting for both spatial and price competition among public cloud providers. We introduce a mixed logit demand model of spatial competition estimable with detailed data of a single firm but only aggregate sales data of a second. We leverage the EM algorithm to tackle the customer level missing data problem of the second firm. Estimation results and counterfactuals show that standard spatial competition economics hold even when distances for cloud latency is trivial.