首页> 外文会议>8th World Multi-Conference on Systemics, Cybernetics and Informatics(SCI 2004) vol.16 >Diagnostics High Leverage Cases and Influential Observations in Regression Analysis
【24h】

Diagnostics High Leverage Cases and Influential Observations in Regression Analysis

机译:回归分析中的诊断高杠杆病例和影响性观察

获取原文
获取原文并翻译 | 示例

摘要

In this article, we first give the probability density function of Andrews-Pregibon's diagnostic statistic. Then we suggest two new diagnostic methods for high leverage cases and influential observations in regression analysis that they based on the multivariate standard distributions, such as, Wishart distribution,rnT~2 distribution, Wilks distribution, and so on. We find that these methods are very successful in assessing influence. They can diagnostic the high leverage cases and influential observations in regression analysis more easily.
机译:在本文中,我们首先给出了Andrews-Pregibon诊断统计量的概率密度函数。然后我们提出了两种新的针对高杠杆案例的诊断方法和回归分析中的有影响力的观察结果,它们基于多元标准分布,例如Wishart分布,rnT〜2分布,Wilks分布等。我们发现这些方法在评估影响力方面非常成功。他们可以在回归分析中更轻松地诊断高杠杆率案例和有影响力的观察结果。

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