基于Pena距离的KL估计的影响分析
Influence Analysis of KL Estimation Based on Pena Distance
DOI: 10.12677/AAM.2021.104100, PDF,   
作者: 王孟孟, 田维琦：贵州民族大学数据科学与信息工程学院，贵州 贵阳
关键词: KL估计；Pena距离；影响分析；KL Estimates； Pena Distance； Influence Analysis
摘要: 利用Pena距离对KL估计的影响分析进行讨论，得到了KL估计的Pena统计量的表达式，并对其性质进行讨论分析，从而得到高杠异常点的判别方法。本文对Pena统计量与Cook统计量的性质进行了比较，得出在一定条件下Pena统计量是优于Cook统计量的结论。通过实例对比分析，得到研究结果表明本文提出的理论和方法是科学合理的。
Abstract: In this paper, the influence analysis of KL estimation is discussed on the Pean distance. The expression of Pena statistics of KL estimation is obtained. The properties of Pena statistics are discussed and analyzed; meanwhile the discrimination of high-leverage outlier is obtained. In this paper, the properties of Pena statistic and Cook statistic are compared, and it is concluded that Pena statistic is better than Cook statistic under certain conditions. Through the example analysis, the research results show that the theory and method proposed in this paper are scientific and reasonable.
文章引用：王孟孟, 田维琦. 基于Pena距离的KL估计的影响分析[J]. 应用数学进展, 2021, 10(4): 923-930. https://doi.org/10.12677/AAM.2021.104100

参考文献

[1] Pena, D. (2005) A New Statistic for Influence in Linear Regression. Technometrics, 47, 1-12. [Google Scholar] [CrossRef] 
[2] 孟丽丽. 基于Pena距离的加权最小二乘估计的影响分析[J]. 数理统计与管理, 2009, 28(2): 252-257.
[3] 胡江. 基于Pena距离的非线性回归模型的影响分析[J]. 大学数学. 2012, 28(5): 80-85.
[4] 胡江, 林金官, 赵彦勇. 基于Pena距离的广义线性回归模型的影响分析[J]. 应用数学, 2017, 30(3): 539-546.
[5] 胡江. 基于Pena距离的几种回归模型的影响分析[D]: [硕士学位论文]. 南京: 东南大学, 2012.
[6] Hu, J., Lin, J.G. and Zhao, Y.Y. (2017) Influence Analysis of Generalized Linear Regression Model Based on Pena Distance. Applied Mathematics, 30, 539-546.
[7] Türkan, S. and Toktamıs, Ö. (2012) Detection of Influential Observations in Ridge Regression and Modified Ridge Regression. Model Assisted Stats & Applications, 7, 91-97. [Google Scholar] [CrossRef] 
[8] Emami, H. and Emami, M. (2016) New Influence Diagnostics in Ridge Regression. Journal of Applied Statistics, 43, 476-489. [Google Scholar] [CrossRef] 
[9] Kashif, M., Amanullah, M. and Aslam, M. (2018) Pena’s Statistic for the Liu Regression. Journal of Statistical Computation and Simulation, 88, 2473-2488. [Google Scholar] [CrossRef] 
[10] Kashif, M., Ullah, M.A. and Aslam, M. (2019) Influential Diagnostics with Pena’s Statistic for the Modified Ridge Regression. Communications in Statistics: Simulation and Computation. [Google Scholar] [CrossRef] 
[11] Kibria, B.M.G. and Lukman, A.F. (2020) A New Ridge-Type Estimator for the Linear Regression Model: Simulations and Applications. Scientifica, 2020, Article ID: 9758378. [Google Scholar] [CrossRef] [PubMed]
[12] Muller, K.E. and Mok, M.C. (1997) The Distribution of Cook’s D Statistic. Communications in Statistics—Theory and Methods, 26, 525-546. [Google Scholar] [CrossRef] [PubMed]
[13] Longley, J.W. (1967) An Appraisal of Least Squares Programs for Electronic Computer from the Point of View of the User. Journal of American Statistical Association, 62, 819-841. [Google Scholar] [CrossRef] 
[14] Belsley, D.A., Kuh, E. and Welsch, R.E. (1989) Regression Diagnostics: Identifying Influential Data and Sources of Collinearity. Wiley, New York.
[15] Cook, R.D. (1977) Detection of Influential Observation in Linear Regression. Technometrics, 19, 15-18. [Google Scholar] [CrossRef] 
[16] Walker, E. and Birch, J. (1989) Influence Measures in Ridge Regression. Technometrics, 30, 221-227. [Google Scholar] [CrossRef] 
[17] Jahufer, A. and Chen, J.B. (2009) Assessing Global Influential Observations in Modified Ridge Regression. Statistics & Probability Letters, 79, 513-518. [Google Scholar] [CrossRef] 

为你推荐