Comparing conditional quantile estimators: rst and second order considerations
نویسنده
چکیده
In this paper, we examine rst and second order asymptotic theory for two estima-tors in a linear quantile model in the case where the response is observed multiple times at xed covariate vectors x 1 ; ; x k. The rst estimator is the regression quantile esti-mator introduced by Koenker and Bassett (1978) while the second estimator is a least squares estimator on the sample quantiles of the response at each x i. In particular, it is shown that, under an i.i.d. error model, the two estimators are asymptotically equivalent to rst order but have diierent second order behaviour.
منابع مشابه
The Second-order Bias and MSE of Quantile Estimators
The finite sample theory using higher order asymptotics provides better approximations of the bias and mean squared error (MSE) for a class of estimators. However, no finite sample theory result is available for the quantile regression and the literature on the quantile regression has been entirely on the first-order asymptotic theory. This paper develops new analytical results on the second-or...
متن کاملConditional Independence Specication Testing for Dependent Processes with Local Polynomial Quantile Regression
We provide straightforward new nonparametric methods for testing conditional independence using local polynomial quantile regression, allowing weakly dependent data. Inspired by Hausmans (1978) speci cation testing ideas, our methods essentially compare two collections of estimators that converge to the same limits under correct speci cation (conditional independence) and that diverge under th...
متن کاملA Direct Approach to Inference in Nonparametric and Semiparametric Quantile Regression Models
This paper makes two main contributions. First, we construct “density-free” confidence intervals and confidence bands for conditional quantiles in nonparametric and semiparametric quantile regression models. They are based on pairs of symmetrized k-NN quantile estimators at two appropriately chosen quantile levels. In contrast to Wald-type confidence intervals or bands based on the asymptotic d...
متن کاملConditional Quantile Estimation for Garch Models
Conditional quantile estimation is an essential ingredient in modern risk management. Although GARCH processes have proven highly successful in modeling financial data it is generally recognized that it would be useful to consider a broader class of processes capable of representing more flexibly both asymmetry and tail behavior of conditional returns distributions. In this paper, we study esti...
متن کاملOn Smooth Statistical Tail Functionals
Many estimators of the extreme value index of a distribution function F that are based on a certain number k n of largest order statistics can be represented as a statistical tail functional, that is a functional T applied to the empirical tail quantile function Q n. We study the asymptotic behavior of such estimators with scale and location invariant functional T under weak second order condit...
متن کامل