当前位置: X-MOL 学术Stat. Sin. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
High-dimensional Varying Index Coefficient Quantile Regression Model
Statistica Sinica ( IF 1.5 ) Pub Date : 2022-01-01 , DOI: 10.5705/ss.202020.0170
Jing Lv , Jialiang Li

Statistical learning evolves quickly with more and more sophisticated models proposed to incorporate the complicated data structure from modern scientific and business problems. Varying index coefficient models extend varying coefficient models and single index models, becoming the latest state-of-the-art for semiparametric regression. This new class of models offers greater flexibility to characterize complicated nonlinear interaction effects in regression analysis. To safeguard against outliers and extreme observations, we consider a robust quantile regression approach to estimate the model parameters in this paper. High-dimensional loading parameters are allowed in our development under reasonable theoretical conditions. In addition, we propose a regularized estimation procedure to choose between linear and non-linear forms for interaction terms. We can simultaneously select significant non-zero loading parameters and identify linear functions in varying index coefficient models, in addition to estimate all the parametric and nonparametric components consistently. Under technical assumptions, we show that the proposed procedure is consistent in variable selection as well as in linear function identification, and the proposed parameter estimation enjoys the oracle property. Extensive simulation studies are carried out to assess the finite sample performance of the proposed method. We illustrate our methods with an environmental health data example.

中文翻译:

高维变指数系数分位数回归模型

统计学习发展迅速,提出了越来越多的复杂模型,以合并来自现代科学和商业问题的复杂数据结构。变指数系数模型扩展了变系数模型和单指数模型,成为半参数回归的最新技术。这类新模型为表征回归分析中复杂的非线性交互效应提供了更大的灵活性。为了防止异常值和极端观察,我们考虑了一种稳健的分位数回归方法来估计本文中的模型参数。在合理的理论条件下,我们的开发允许高维载荷参数。此外,我们提出了一个正则化的估计程序,用于在交互项的线性和非线性形式之间进行选择。除了一致地估计所有参数和非参数分量外,我们还可以同时选择重要的非零载荷参数并识别不同指数系数模型中的线性函数。在技​​术假设下,我们表明所提出的程序在变量选择和线性函数识别方面是一致的,并且所提出的参数估计具有预言性。进行了广泛的模拟研究以评估所提出方法的有限样本性能。我们用环境健康数据示例来说明我们的方法。除了一致地估计所有参数和非参数分量外,我们还可以同时选择重要的非零载荷参数并识别不同指数系数模型中的线性函数。在技​​术假设下,我们表明所提出的程序在变量选择和线性函数识别方面是一致的,并且所提出的参数估计具有预言性。进行了广泛的模拟研究以评估所提出方法的有限样本性能。我们用环境健康数据示例来说明我们的方法。除了一致地估计所有参数和非参数分量外,我们还可以同时选择重要的非零载荷参数并识别不同指数系数模型中的线性函数。在技​​术假设下,我们表明所提出的程序在变量选择和线性函数识别方面是一致的,并且所提出的参数估计具有预言性。进行了广泛的模拟研究以评估所提出方法的有限样本性能。我们用环境健康数据示例来说明我们的方法。并且提出的参数估计享有oracle属性。进行了广泛的模拟研究以评估所提出方法的有限样本性能。我们用环境健康数据示例来说明我们的方法。并且提出的参数估计享有oracle属性。进行了广泛的模拟研究以评估所提出方法的有限样本性能。我们用环境健康数据示例来说明我们的方法。
更新日期:2022-01-01
down
wechat
bug