arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1409.3886stat.ME
收藏

关于残差的一个非参数概念及其应用

On a Nonparametric Notion of Residual and its Applications

Rohit Kumar Patra, Bodhisattva Sen, Gabor Szekely

摘要:

设$(X, \mathbf{Z})$是$\mathbb{R} \times \mathbb{R}^d$中的连续随机向量,$d \ge 1$。在本文中,我们定义了一个非参数残差的概念$X$对$\mathbf{Z}$,总是独立的预测$\mathbf{Z}$。我们研究了它的性质,并表明,建议的残差的概念与通常的残差(误差)在多元正态回归模型相匹配。给定$\mathbb{R} \times \mathbb{R} \times \mathbb{R}^d$中的随机向量$(X, Y, \mathbf{Z})$,我们使用残差的这个概念来表明,给定$\mathbf{Z}$,$X$和$Y$之间的条件独立性等价于残差($X$对$\mathbf{Z}$和$Y$对$\mathbf{Z}$)和$\mathbf{Z}$的相互独立性。该结果用于开发条件独立性的测试。我们提出了一个自助方案,以近似这个测试的临界值。我们比较了建议的测试,这是很容易实现的,与现有的一些程序,通过模拟研究。

英文摘要:

Let $(X, \mathbf{Z})$ be a continuous random vector in $\mathbb{R} \times \mathbb{R}^d$, $d \ge 1$. In this paper, we define the notion of a nonparametric residual of $X$ on $\mathbf{Z}$ that is always independent of the predictor $\mathbf{Z}$. We study its properties and show that the proposed notion of residual matches with the usual residual (error) in a multivariate normal regression model. Given a random vector $(X, Y, \mathbf{Z})$ in $\mathbb{R} \times \mathbb{R} \times \mathbb{R}^d$, we use this notion of residual to show that the conditional independence between $X$ and $Y$, given $\mathbf{Z}$, is equivalent to the mutual independence of the residuals (of $X$ on $\mathbf{Z}$ and $Y$ on $\mathbf{Z}$) and $\mathbf{Z}$. This result is used to develop a test for conditional independence. We propose a bootstrap scheme to approximate the critical value of this test. We compare the proposed test, which is easily implementable, with some of the existing procedures through a simulation study.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑