### Abstract

Lingua originale | English |
---|---|

pagine (da-a) | 1471082X1982552- |

Numero di pagine | 17 |

Rivista | Statistical Modelling |

Stato di pubblicazione | Published - 2019 |

### Fingerprint

### All Science Journal Classification (ASJC) codes

- Statistics and Probability
- Statistics, Probability and Uncertainty

### Cita questo

*Statistical Modelling*, 1471082X1982552-.

**A penalized approach to covariate selection through quantile regression coefficient models.** / Chiodi, Marcello; Sottile, Gianluca; Matteo, Bottai; Sottile, Gianluca.

Risultato della ricerca: Article

*Statistical Modelling*, pagg. 1471082X1982552-.

}

TY - JOUR

T1 - A penalized approach to covariate selection through quantile regression coefficient models

AU - Chiodi, Marcello

AU - Sottile, Gianluca

AU - Matteo, Bottai

AU - Sottile, Gianluca

PY - 2019

Y1 - 2019

N2 - The coefficients of a quantile regression model are one-to-one functions of the order of the quantile. In standard quantile regression (QR), different quantiles are estimated one at a time. Another possibility is to model the coefficient functions parametrically, an approach that is referred to as quantile regression coefficients modeling (QRCM). Compared with standard QR, the QRCM approach facilitates estimation, inference and interpretation of the results, and generates more efficient estimators. We designed a penalized method that can address the selection of covariates in this particular modelling framework. Unlike standard penalized quantile regression estimators, in which model selection is quantile-specific, our approach permits using information on all quantiles simultaneously. We describe the estimator, provide simulation results and analyse the data that motivated the present article. The proposed approach is implemented in the qrcmNP package in R.

AB - The coefficients of a quantile regression model are one-to-one functions of the order of the quantile. In standard quantile regression (QR), different quantiles are estimated one at a time. Another possibility is to model the coefficient functions parametrically, an approach that is referred to as quantile regression coefficients modeling (QRCM). Compared with standard QR, the QRCM approach facilitates estimation, inference and interpretation of the results, and generates more efficient estimators. We designed a penalized method that can address the selection of covariates in this particular modelling framework. Unlike standard penalized quantile regression estimators, in which model selection is quantile-specific, our approach permits using information on all quantiles simultaneously. We describe the estimator, provide simulation results and analyse the data that motivated the present article. The proposed approach is implemented in the qrcmNP package in R.

UR - http://hdl.handle.net/10447/347847

UR - http://smj.sagepub.com/archive/

M3 - Article

SP - 1471082X1982552-

JO - Statistical Modelling

JF - Statistical Modelling

SN - 1471-082X

ER -