دورية أكاديمية
Estimation and convergence rates in the distributional single index model
| العنوان: | Estimation and convergence rates in the distributional single index model |
|---|---|
| المؤلفون: | Balabdaoui, Fadoua, Henzi, Alexander, Looser, Lukas |
| المصدر: | Statistica Neerlandica |
| بيانات النشر: | Wiley-Blackwell |
| سنة النشر: | 2024 |
| المجموعة: | ETH Zürich Research Collection |
| مصطلحات موضوعية: | monotone regression, isotonic distributional regression, single index model |
| الوصف: | The distributional single index model is a semiparametric regression model in which the conditional distribution functions P(Y ≤ y | X = x) = F₀(θ₀(x), y) of a real-valued outcome variable Y depend on d-dimensional covariates X through a univariate, parametric index function θ₀(x), and increase stochastically as θ₀(x) increases. We propose least squares approaches for the joint estimation of θ₀ and F₀ in the important case where θ₀(x) = αᵀ₀x and obtain convergence rates of n⁻¹/³, thereby improving an existing result that gives a rate of n⁻¹/⁶. A simulation study indicates that the convergence rate for the estimation of α₀ might be faster. Furthermore, we illustrate our methods in an application on house price data that demonstrates the advantages of shape restrictions in single index models. ; ISSN:0039-0402 |
| نوع الوثيقة: | article in journal/newspaper |
| وصف الملف: | application/application/pdf |
| اللغة: | English |
| العلاقة: | info:eu-repo/semantics/altIdentifier/wos/001187166900001; http://hdl.handle.net/20.500.11850/667298Test |
| DOI: | 10.3929/ethz-b-000667298 |
| الإتاحة: | https://doi.org/20.500.11850/667298Test https://doi.org/10.3929/ethz-b-000667298Test https://doi.org/10.1111/stan.12336Test https://hdl.handle.net/20.500.11850/667298Test |
| حقوق: | info:eu-repo/semantics/openAccess ; http://creativecommons.org/licenses/by-nc-nd/4.0Test/ ; Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International |
| رقم الانضمام: | edsbas.83781E61 |
| قاعدة البيانات: | BASE |
| DOI: | 10.3929/ethz-b-000667298 |
|---|