Abstract
We present an estimating framework for quantile regression where the usual L1-norm objective function is replaced by its smooth parametric approximation. An exact path-following algorithm is derived, leadingto the well-known ‘basic’ solutions interpolating exactly a number of observations equal to the number ofparameters being estimated. We discuss briefly possible practical implications of the proposed approach, such as early stopping for large data sets, confidence intervals, and additional topics for future research.
Lingua originale | English |
---|---|
pagine (da-a) | 1557-1569 |
Numero di pagine | 0 |
Rivista | Journal of Statistical Computation and Simulation |
Volume | 82 |
Stato di pubblicazione | Published - 2012 |
All Science Journal Classification (ASJC) codes
- ???subjectarea.asjc.2600.2613???
- ???subjectarea.asjc.2600.2611???
- ???subjectarea.asjc.1800.1804???
- ???subjectarea.asjc.2600.2604???