将模糊集理论引入多元线性回归中，通过模糊控制变量，可以得出更符合实际，也更容易为人所理解的回归模型。
By introducing fuzzy control variable, the paper proposes a fuzzy multiple linear regression model which can get more effective and more understandable fuzzy regression expression.
在此基础上，通过逐步回归分析确定用于高速公路事件持续时间预测的最佳变量组合并建立多元线性回归模型。
Then, stepwise regression analysis is used to select a best group of factors for the prediction of expressway incident duration, and the multiple linear regression model is established.
实证部分主要包括多变量检验、单变量t检验、趋势图分析以及多元线性回归分析等。
Evidences include some of the major multi-variable tests, a single variable t tests, trend analysis and multiple linear regression analysis.
目的 ：在多元线性模型中 ，估计各自变量的相对重要性。
Objective The work was designed to estimate the relative importance of each variable in multiple linear model.
对多元线性回归模型参数的预测，转化为对其变量集合的增广矩阵的叉积阵的预测。
Prediction to the regression parameters was converted to predict cross product matrix of the variable augmented matrix.
结论：在形态学上进行多元线性回归分析，可以通过某些已知变量来预测某个未知变量。
Conclusions: The multiple regression analysis may predict unknown variable from known variables in morphological application.
研究了任意秩多元线性模型中最优线性无偏预测的稳健性，即对任一线性可预测变量，得到了其关于协方差矩阵具有稳健性的充要条件。
The conditional optimal prediction of the conditional predictable variable in the multivariate linear model with arbitrary rank and linear equality constrains was investigated.
然而，在多元线性分析方法中，当求解因变量对自变量的回归时，得到的组合系数往往均不为零，因此这种回归模型的主要缺点是缺乏可解释性。
However, when try to regression independent variables to the dependent variables in multivariate analysis, the coefficients are all non-zero. So these models lack of interpretation.
以遥感本底值为因变量和所筛选的评价指标为自变量建立多元线性回归方程。
In each index type, there was an index was selected as the evaluation index for its correlation variables was the biggest.
以遥感本底值为因变量和所筛选的评价指标为自变量建立多元线性回归方程。
In each index type, there was an index was selected as the evaluation index for its correlation variables was the biggest.
应用推荐