Asymptotic confidence bands for the histogram regression estimator
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915822527578112 |
|---|---|
| author | Neumeyer, Natalie Rabe, Jan Trabs, Mathias |
| author_facet | Neumeyer, Natalie Rabe, Jan Trabs, Mathias |
| contents | Asymptotic uniform confidence bands are constructed for a multivariate nonparametric regression model with heteroscedastic noise, employing histogram estimators under flexible partition conditions. The construction is especially applicable to unsmooth regression functions of Hölder regularity less than one. While the radius of the confidence bands could be approximated via the Gumbel distribution, our construction does not depend on an extreme value distribution, but instead can be explicitly calculated for the chosen partition. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_12391 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Asymptotic confidence bands for the histogram regression estimator Neumeyer, Natalie Rabe, Jan Trabs, Mathias Statistics Theory Methodology 62G08, 62G20, 62H12 Asymptotic uniform confidence bands are constructed for a multivariate nonparametric regression model with heteroscedastic noise, employing histogram estimators under flexible partition conditions. The construction is especially applicable to unsmooth regression functions of Hölder regularity less than one. While the radius of the confidence bands could be approximated via the Gumbel distribution, our construction does not depend on an extreme value distribution, but instead can be explicitly calculated for the chosen partition. |
| title | Asymptotic confidence bands for the histogram regression estimator |
| topic | Statistics Theory Methodology 62G08, 62G20, 62H12 |
| url | https://arxiv.org/abs/2508.12391 |