Quantile regression in high-dimension with breaking

arXiv1302.4244MaRDI QIDQ6239705FDOQ6239705

Publication date: 18 February 2013

Abstract: The paper considers a linear regression model in high-dimension for which the predictive variables can change the influence on the response variable at unknown times (called change-points). Moreover, the particular case of the heavy-tailed errors is considered. In this case, least square method with LASSO or adaptive LASSO penalty can not be used since the theoretical assumptions do not occur or the estimators are not robust. Then, the quantile model with SCAD penalty or median regression with LASSO-type penalty allows, in the same time, to estimate the parameters on every segment and eliminate the irrelevant variables. We show that, for the two penalized estimation methods, the oracle properties is not affected by the change-point estimation. Convergence rates of the estimators for the change-points and for the regression parameters, by the two methods are found. Monte-Carlo simulations illustrate the performance of the methods.

Mathematics Subject Classification ID

Asymptotic properties of parametric estimators (62F12) Ridge regression; shrinkage estimators (Lasso) (62J07)

This page was built for publication: Quantile regression in high-dimension with breaking

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6239705)