Performance of some variable selection methods when multicollinearity is present
Performance of some variable selection methods when multicollinearity is present
复制标题
DOI：
10.1016/j.chemolab.2004.12.011
复制
发表时间：
2005-07-28
影响因子：
3.9
通讯作者：
Jun, CH
中科院分区：
文献类型：
--
作者：
Chong, IG;Jun, CH
变量选择是许多科学工程师面临的重要实际问题之一。虽然PLS（偏最小二乘）回归结合VIP（投影中的变量重要性）得分通常用于多重共线性时，变量之间存在，但很少有关于其使用及其性能的指导方针。本文的目的是探讨VIP方法的本质，并通过计算机仿真实验与其他方法进行比较。我们设计了108个实验，其中观察结果来自考虑四个因素的真实模型-相关预测因子数量的比例，预测因子之间相关性的大小，回归系数的结构以及信噪比的大小。采用混淆矩阵、Lasso法和逐步法对PLS的性能进行评价。我们还讨论了VIP方法的适当截止值，以提高其性能。作为仿真结果，给出了使用VIP方法的一些实用提示。(c) 2005 Elsevier B.V.版权所有
Variable selection is one of the important practical issues for many scientific engineers. Although the PLS (partial least squares) regression combined with the VIP (variable importance in the projection) scores is often used when the multicollinearity, is present among variables, there are few guidelines about its uses as well as its performance. The purpose of this paper is to explore the nature of the VIP method and to compare with other methods through computer simulation experiments. We design 108 experiments where observations are generated from true models considering four factors-the proportion of the number of relevant predictors, the magnitude of correlations between predictors, the structure of regression coefficients, and the magnitude of signal to noise. Confusion matrix is adopted to evaluate the performance of PLS, the Lasso, and stepwise method. We also discuss the proper cutoff value of the VIP method to increase its performance. Some practical hints for the use of the VIP method are given as simulation results. (c) 2005 Elsevier B.V. All rights reserved.