...
首页> 外文期刊>Computational statistics & data analysis >Resampling for checking linear regression models via non-parametric regression estimation
【24h】

Resampling for checking linear regression models via non-parametric regression estimation

机译:通过非参数回归估计重新采样以检查线性回归模型

获取原文
获取原文并翻译 | 示例
           

摘要

Let us consider the fixed regression model, Y_t = m(X_t) + ε_t, t = 1, … , n, and assume that the random errors, {ε_t}, follow an ARMA- type dependence structure. The purpose of this paper is to study the application of the bootstrap test to check that the unknown regression function, m, follows a general linear model of the type: H_0 : m ∈M = {m_0(·) = A~t (·)θ: θ ∈ Θ ∈R~q} with A being a functional of R in R~q. In a previous paper, Gonzalez-Manteiga and Vilar-Fernandez (1995) proposed a test, D = d~2((m-circumflex)_n, m_((0-circumflex)_n)), based on the Cramer-von-Mises-type functional distance, where (m-circumflex)_n is a Gasser-Muller-type non-parametric estimator of m, and m_((0-circumflex)_n) is a member of the family M that is closest to (m-circumflex)_n. In this work, two bootstrap algorithms are considered, where the dependence structure of the errors is taken into account. A broad simulation study and an applied example show the good behavior of the bootstrap test.
机译:让我们考虑固定回归模型Y_t = m(X_t)+ε_t,t = 1,…,n,并假设随机误差{ε_t}遵循ARMA类型的依存结构。本文的目的是研究引导测试的应用,以检查未知回归函数m是否遵循以下类型的通用线性模型:H_0:m∈M= {m_0(·)= A〜t(· )θ:θ∈Θ∈R〜q},其中A是R〜q中R的函数。在以前的论文中,Gonzalez-Manteiga和Vilar-Fernandez(1995)基于Cramer-von-提出了一个检验D = d〜2((m-circumflex)_n,m _((0-circumflex)_n))。 Mises型函数距离,其中(m-circumflex)_n是m的Gasser-Muller型非参数估计量,而m _(((0-circumflex)_n)是最接近(m)的族M的成员-circumflex)_n。在这项工作中,考虑了两种自举算法,其中考虑了错误的依赖性结构。广泛的仿真研究和应用示例表明了自举测试的良好行为。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号