Smoothing quantile regressions
Preprint
Abstract
We propose to smooth the entire objective function, rather than only the check function, in a linear quantile regression context. Not only does the resulting smoothed quantile regression estimator yield a lower mean squared error and a more accurate Bahadur-Kiefer representation than the standard estimator, but it is also asymptotically differentiable. We exploit the latter to propose a quantile density estimator that does not suffer from the curse of dimensionality. This means estimating the conditional density function without worrying about the dimension of the covariate vector. It also allows for two-stage efficient quantile regression estimation. Our asymptotic theory holds uniformly with respect to the bandwidth and quantile level. Finally, we propose a rule of thumb for choosing the smoothing bandwidth that should approximate well the optimal bandwidth. Simulations confirm that our smoothed quantile regression estimator indeed performs very well in finite samples.Keywords
All Related Versions
This publication has 36 references indexed in Scilit:
- Smoothed quantile regression for panel dataJournal of Econometrics, 2016
- A direct approach to inference in nonparametric and semiparametric quantile modelsJournal of Econometrics, 2016
- Asymptotic normality of Powell’s kernel estimatorAnnals of the Institute of Statistical Mathematics, 2010
- Efficient estimation in dynamic conditional quantile modelsJournal of Econometrics, 2010
- Bootstrap variance estimation for Nadaraya quantile estimatorTEST, 2009
- Weak identification robust tests in an instrumental quantile modelJournal of Econometrics, 2008
- Conditional empirical likelihood estimation and inference for quantile regression modelsJournal of Econometrics, 2008
- An MCMC approach to classical estimationJournal of Econometrics, 2003
- Galton, Edgeworth, Frisch, and prospects for quantile regression in econometricsJournal of Econometrics, 2000
- Estimating the asymptotic covariance matrix for quantile regression models a Monte Carlo studyJournal of Econometrics, 1995