Feifan Wang

University of Connecticut · Economics · 2026–27 job market

Fields

Econometrics, Finance

Job market paper

Bootstrap Inference for Factor-Augmented Quantile Regression

This paper develops inference for factor-augmented quantile regression (FAQR) that accounts for both factor-estimation uncertainty and serial dependence in the second-stage regression disturbances. Within a smoothed FAQR framework, I derive the limiting distribution of the estimator and show that factor estimation can generate a non-negligible, quantile-specific asymptotic bias. I then propose a two-step dependent wild bootstrap that reproduces both factor-estimation uncertainty and serial dependence in the quantile score, and establish its asymptotic validity. Monte Carlo simulations show that the proposed method provides more accurate size control than existing inference methods. An application to U.S. real GDP growth shows that accounting for factor estimation error can increase sampling uncertainty, particularly in the tails.