A generalized quantile regression model |
| |
Authors: | Vahid Nassiri Ignace Loris |
| |
Institution: | 1. Department of Mathematics , Vrije Universiteit Brussel , Brussels , Belgium;2. Département de Mathématique , Université Libre de Bruxelles , Brussels , Belgium |
| |
Abstract: | A new class of probability distributions, the so-called connected double truncated gamma distribution, is introduced. We show that using this class as the error distribution of a linear model leads to a generalized quantile regression model that combines desirable properties of both least-squares and quantile regression methods: robustness to outliers and differentiable loss function. |
| |
Keywords: | quantile regression log-concave density penalization soft thresholding outlier long tail |
|
|