Multivariate multiple linear regression based on the minimum sum of absolute errors criterion
Multivariate multiple linear regression based on the minimum sum of absolute errors criterion
复制标题
基于最小绝对误差和准则的多元多元线性回归
DOI：
10.1016/0377-2217(94)90144-9
复制
发表时间：
1994
影响因子：
6.4
通讯作者：
P. Korhonen
中科院分区：
文献类型：
--
作者：
S. Narula;P. Korhonen
我们提出了最小绝对误差和 (MSAE) 标准来估计多元多元线性回归模型的未知参数。与流行的最小二乘法相比，它对异常值不太敏感。多元多元线性回归问题可以被视为多标准决策问题。使用 MSAE 准则，可以将估计问题表述为多目标线性规划问题并将其求解。我们用双标准示例来说明这个想法。
We propose the minimum sum of absolute errors (MSAE) criterion for estimating the unknown parameters of a multivariate multiple linear regression model. It is less sensitive to outliers than the popular least squares procedure. A multivariate multiple linear regression problem may be viewed as a multiple criteria decision problem. Using the MSAE criterion the estimation problem can be formulated and solved as a multiple objective linear programming problem. We illustrate the idea with a bicriteria example.