| 基于互信息的变量选择方法 |
| |
| 引用本文： | 周生彬,黄叶金.基于互信息的变量选择方法[J].统计与决策,2020(1):20-23. |
| |
| 作者姓名： | 周生彬 黄叶金 |
| |
| 作者单位： | 哈尔滨师范大学数学科学学院;清华五道口金融学院 |
| |
| 摘 要： | 文章基于解释变量与被解释变量之间的互信息提出一种新的变量选择方法:MI-SIS。该方法可以处理解释变量数目p远大于观测样本量n的超高维问题,即p=O(exp(nε))ε>0。另外,该方法是一种不依赖于模型假设的变量选择方法。数值模拟和实证研究表明,MI-SIS方法在小样本情形下能够有效地发现微弱信号。
|
| 关 键 词： | 变量选择 互信息 非参数密度估计 超高维数据分析 |
Variable Selection Method Based on Mutual Information |
| |
| Authors: | Zhou Shengbin Huang Yejin |
| |
| Institution: | (School of Mathematical Sciences,Harbin Normal University,Harbin 150025,China;PBC Shcool of Finance,Tsinghua University,Beijing 100083,China) |
| |
| Abstract: | This paper proposes a new variable screening method based on mutual information between explanatory variables and explained variables,namely MI-SIS.This method can deal with the ultrahigh dimension problem where the number of explanatory variablesp]is much larger than the observed sample sizen],that is,p=O(exp(nε)),ε>0.].In addition,the proposed method is a variable selection method independent of model assumptions.Numerical simulation and empirical study show that the MI-SIS method can effectively detect weak signals in small samples. |
| |
| Keywords: | variable selection mutual information non-parametric density estimation ultrahigh dimension data analysis |
| 本文献已被 维普 等数据库收录！ |
|
