On nonparametric regression estimators based on regression quantiles

From MaRDI portal





In the classical regression model \(Y_ i=h(x_ i)+\epsilon_ i\), \(i=1,...,n\), \textit{K. Cheng} [Sankhya, Ser. A 46, 287-302 (1984; Zbl 0575.62040)] introduced linear combinations of regression quantiles as a new class of etimators for the unknown regression function h(x). The asymptotic properties studied by Cheng are reconsidered. We obtain a sharper strong consistency rate and we improve on the conditions for asymptotic normality by proving a new result on the remainder term in the Bahadur representation for regression quantiles.











This page was built for publication: On nonparametric regression estimators based on regression quantiles

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3802410)