PLS1回归对多变量信息的综合与筛选作用分析

发布时间：2018-04-17 02:31

  本文选题：PLS回归方法 + 变量多重相关性　； 参考：《数理统计与管理》1998年04期

【摘要】：王惠文，ＰＬＳ１回归对多变量信息的综合与筛选作用分析，数理统计与管理，１９９８，１７（４），４６～４９。本文讨论了ＰＬＳ１回归对多变量系统中的信息进行综合与筛选的工作策略。通过例证分析指出，ＰＬＳ１回归方法可以有效地提取对系统解释性最强的综合变量，排除重叠信息或无解释意义的信息干扰，，从而较好地克服变量多重相关性在系统建模中的不良作用
[Abstract]:Analysis of the effect of Wang Huiwen's PLS1 regression on the Synthesis and screening of Multivariate Information, Mathematical Statistics and ManagementIn this paper, the strategy of synthesizing and screening information in multivariable systems by PLS1 regression is discussed.Through the analysis of examples, it is pointed out that the method of PLS1 regression can effectively extract the most explanatory comprehensive variables and eliminate the interference of overlapping information or non-explanatory information, so as to overcome the adverse effect of multiple correlation of variables in system modeling.
【基金】：自然科学基金
【分类号】：C931.1


本文编号：1761686