Lucas Girard – Job Market Candidate 2026

Personal website:

https://faculty.crest.fr/lgirard

Contact:

lucas.girard@ensae.fr

References:

  • Pr. Xavier D’Haultfoeuille – CREST, Groupe ENSAE-ENSAI, Institut Polytechnique de Paris
  • Pr. Elia Lapenta – CREST, Groupe ENSAE-ENSAI, Institut Polytechnique de Paris
  • Pr. Frédéric Loss – Cergy Paris University, THEMA
  • Pr. Guillaume Lecué – ESSEC Business School

Research fields:

Primary fields: Econometric Theory (non-asymptotic inference, causal inference, non parametric estimation)
Secondary fields: Applied Microeconometrics (segregation indices)

Presentation: 

Between 2017 and 2021, I completed my PhD in econometrics at CREST under the supervision of Xavier D’Haultfoeuille.
I worked as a Teaching Fellow (2020-2022) and a Teaching Coordinator in Mathematics (2022-2024) at ENSAE Paris.
I have been working as a postdoctoral researcher at CREST since September 2024 under the supervision of Elia Lapenta.
I am interested in econometric theory and its application, with three main themes of research as of now:

  • 1. Reliable (robust to the “small-unit bias”) measures of polarization/segregation
  • 2. Nonasymptotically valid (coverage at least the nominal level for finite sample sizes) confidence intervals in linear regressions and in more general settings
  • Reproducing Kernel Hilbert Spaces (RKHS) estimation tools in Nonparametric Instrumental Variables (NPIV) regressions

Job Market Paper:

Can we have it all? Non-asymptotically valid and asymptotically exact confidence intervals for expectations and linear regressions
Abstract: We contribute to bridging the gap between large- and finite-sample inference by studying confidence sets (CSs) that are both non-asymptotically valid and asymptotically exact uniformly (NAVAE) over semi-parametric statistical models. NAVAE CSs are not easily obtained; for instance, we show they do not exist over the set of Bernoulli distributions. We first derive a generic sufficient condition: NAVAE CSs are available as soon as uniform asymptotically exact CSs are. Second, building on that connection, we construct closed-form NAVAE confidence intervals (CIs) in two standard settings – scalar expectations and linear combinations of OLS coefficients – under moment conditions only. For expectations, our sole requirement is a bounded kurtosis. In the OLS case, our moment constraints accommodate heteroskedasticity and weak exogeneity of the regressors. Under those conditions, we enlarge the Central Limit Theorem-based CIs, which are asymptotically exact, to ensure non-asymptotic guarantees. Those modifications vanish asymptotically so that our CIs coincide with the classical ones in the limit. We illustrate the potential and limitations of our approach through a simulation study.