WEKO3
アイテム
Sparse quantile regression via ℓ０-penalty
http://hdl.handle.net/10086/80946
http://hdl.handle.net/10086/80946055bdd9a-ca83-4d47-994c-3ece8407f4d4
| Item type | デフォルトアイテムタイプ（フル）その２(1) | |||||
|---|---|---|---|---|---|---|
| 公開日 | 2023-11-06 | |||||
| タイトル | ||||||
| タイトル | Sparse quantile regression via ℓ０-penalty | |||||
| 言語 | en | |||||
| 作成者 |
本田, 敏雄
× 本田, 敏雄 |
|||||
| アクセス権 | ||||||
| アクセス権 | metadata only access | |||||
| アクセス権URI | http://purl.org/coar/access_right/c_14cb | |||||
| 主題 | ||||||
| 言語 | en | |||||
| 主題Scheme | Other | |||||
| 主題 | selection consistency | |||||
| 主題 | ||||||
| 言語 | en | |||||
| 主題Scheme | Other | |||||
| 主題 | high-dimensional information criteria | |||||
| 主題 | ||||||
| 言語 | en | |||||
| 主題Scheme | Other | |||||
| 主題 | B-spline basis | |||||
| 主題 | ||||||
| 言語 | en | |||||
| 主題Scheme | Other | |||||
| 主題 | additive models | |||||
| 主題 | ||||||
| 言語 | en | |||||
| 主題Scheme | Other | |||||
| 主題 | varying coefficient models | |||||
| 出版者 | ||||||
| 出版者 | Graduate School of Economics, Hitotsubashi University | |||||
| 日付 | ||||||
| 日付 | 2023-11-01 | |||||
| 日付タイプ | Issued | |||||
| 言語 | ||||||
| 言語 | eng | |||||
| 資源タイプ | ||||||
| 資源タイプ識別子 | http://purl.org/coar/resource_type/c_18gh | |||||
| 資源タイプ | technical report | |||||
| 出版タイプ | ||||||
| 出版タイプ | VoR | |||||
| 出版タイプResource | http://purl.org/coar/version/c_970fb48d4fbd8a85 | |||||
| 関連情報 | ||||||
| 関連タイプ | isPartOf | |||||
| 識別子タイプ | HDL | |||||
| 関連識別子 | https://hdl.handle.net/10086/81451 | |||||
| 関連名称 | Discussion papers ; No. 2023-03 | |||||
| 関連情報 | ||||||
| 関連タイプ | isReplacedBy | |||||
| 関連名称 | This version has been revised. The new version is available at https://hdl.handle.net/10086/81451. | |||||
| Sponsorship | ||||||
| 値 | Honda’s research is supported by JSPS KAKENHI Grant Number JP20K11705. | |||||
| 抄録（第三者提供不可） | ||||||
| 値 | We consider model selection via ℓ0-penalty, almost equivalently model selection via information criterion, for high-dimensional sparse quantile regression models. We deal with linear models, additive models, and varying coefficient models in a unified way and establish model selection consistency results rigorously when the size of relevant index set goes to infinity. The treatment of this situation is challenging and the theoretical novelty of our results is important because such information criteria are commonly used in practice. In this paper, we consider two different setups and propose tuning parameters in the ℓ0-penalty and information criterion to these setups. | |||||
