Working papers

Abstract: The differentiated products demand model initiated by Berry (1994) and Berry, Levinsohn, and Pakes (1995) is the workhorse model for demand estimation with market-level data. This model uses random coefficients to account for unobserved preference heterogeneity. The shape of the distribution of random coefficients matters greatly for many counterfactual quantities, such as the pass-through. In this paper, we develop new econometric tools to test this distribution and improve its estimation under a flexible parametrization. In particular, we construct new instruments that are designed to detect deviations from the underlying distribution of random coefficients. Then, we develop a formal moment-based specification test on the distribution of random coefficients. Next, we show that our instruments can strengthen the identifying power of the moment conditions used for estimation. Finally, we validate our approach with Monte Carlo simulations and an empirical application using data on car purchases in Germany. We show that these methods extend to the mixed logit demand model (with individual-level data).

Abstract: Antimicrobial resistance (AMR) increases hospital stays, medical costs and mortality. Antibiotic consumption and resulting selective pressure on bacteria can create AMR. We study the role of AMR on changes in prescriptions of antibiotics in France for treating bladder inflammation (cystitis) using a representative sample of general practitioners between 2002 and 2019. Effects of resistance on demand and substitution behavior are identified via a random coefficient logit model, controlling for the endogeneity of resistance using antibiotics sales in veterinary medicine. As resistance increases, physicians substitute to other drugs, and we test whether physicians consider predictable resistance evolution in their decisions. We perform counterfactual analysis assessing the impact of decreasing veterinary use of antibiotics and limiting fluoroquinolone use to treat cystitis. Both policies reduce resistance against fluoroquinolones but have opposite effects on substitution behavior and consumer surplus. Finally, we propose a method for the optimal pricing of rapid bacterial detection and antibiotic susceptibility testing. 

Work in progress