Max Lesellier will defend his thesis on Thursday 22 June at 16:00 (Auditorium 3 and zoom)
«Essays in Structural Microeconometrics»
Supervisors: Professor Christian Bontemps and Professor Nour Meddahi
To attend the conference, please contact the secretariat Christelle Fotso Tatchum
Memberships are:
- Christian Bontemps : Professor, ENAC-TSE-R Supervisor
- Nour Meddahi : UT Capitole – Directeur de l’ED-TSE Co-supervisor
- Mathias Reynaert : Professor, UT Capitole President
- Cristina Gualdani : Professor, University of Queen Mary Examinator
- Jean François Houde :Professor, University of Wisconsin-Madison Rapporteur
- M. Quang Vuong : Professor, University of New-York Rapporteur
- M. Steven Berry : Professor, University of Yale reviewer
Abstract :
In this thesis, I develop new econometric methods to test and relax statistical or equilibrium restrictions that are commonly assumed in popular industrial organization models including the random coefficient logit model, entry games, and optimal contracts. I then apply these methods to investigate how the usual assumptions affect the results obtained in several relevant empirical examples. This thesis is organized into three chapters.
The first chapter of my thesis is entitled "Testing and Relaxing Distributional Assumptions on Random Coefficients in Demand Models''. This chapter is co-authored with two fellow graduate students Hippolyte Boucher and Gökçe Gökkoca. We provide a method to test and relax the distributional assumptions on random coefficients in the differentiated products demand model initiated by Berry (1994) and Berry, Levinsohn and Pakes (1995). This model is the workhorse model for demand estimation with market-level data and it uses random coefficients to account for unobserved preference heterogeneity. In this chapter, we provide a formal moment-based specification test on the distribution of random coefficients, which allows researchers to test the chosen specification (for instance normality) without re-estimating the model under a more flexible parametrization. The moment conditions (or equivalently the instruments) chosen for the test are designed to maximize the power of the test when the distribution of Random Coefficients is misspecified. By exploiting the duality between estimation and testing, we show that these instruments can also improve the estimation of the BLP model under a flexible parametrization (here, we consider the case of the Gaussian mixture). Finally, we validate our approach with Monte Carlo simulations and an empirical application using data on car purchases in Germany.
The second chapter is entitled: "Moment Inequalities for Entry Games with Heterogeneous Types". This chapter is coauthored with my advisor Christian Bontemps and Rohit Kumar. We develop new methods to simplify the estimation of entry games when the equilibrium selection mechanism is unrestricted. In particular, we develop an algorithm that allows us to recursively select a relevant subset of inequalities that sharply characterize the set of admissible parameters. Then, we propose a way to circumvent the problem of deriving an easy-to-compute and competitive critical value by smoothing the minimum function. In our case, it allows us to obtain a pivotal test statistic that eliminates "numerically” the non-binding moments. We show that we recover a consistent confidence region by letting the smoothing parameter increase with the sample size. Interestingly, we show that our procedure can easily be adapted to the case with covariates including continuous ones. Finally, we conduct full-scale Monte Carlo simulations to assess the performance of our new estimation procedure.
The third chapter is entitled "Identification and Estimation of Incentive Contracts under Asymmetric Information: an application to the French Water Sector". This chapter has its roots in a project Christian Bontemps and David Martimort started many years ago. We develop a Principal-Agent model to represent management contracting for public-service delivery. A firm (the Agent) has private knowledge of its marginal cost of production. The local public authority (the Principal) cares about the consumers' net surplus from consuming the services and the (weighted) firm's profit. Contractual negotiation is modeled as the choice by the privately informed firm within a menu of options determining both the unit-price charged to consumers and the fixed fee. Our theoretical model characterizes optimal contracting in this environment. We then explicitly study the nonparametric identification of the model and perform a semi-parametric estimation on a dataset coming from the 2004 wave of a survey from the French Environment Institute.
