估计Verhulst模型中参数的线性规划方法及应用

Estimation of Verhulst Model Parameter Based on Linear Programming

估计灰色Verhulst模型中的参数通常采用最小二乘准则,而在模型精度检验时又经常采用平均相对误差.本文主要在平均相对误差达到最小准则或最大相对误差达到最小准则下,阐明了Verhulst模型中参数估计问题可转化为线性规划问题,可以利用线性规划方法估计Verhulst模型中的参数.实际应用表明本文的方法是可行的且有效的,比传统方法预测精度高.

Estimation of Verhulst＇ s Model parameter usually adopts least square criterion, but testing model precision often use average relative error. Under the norm of the minimizing the average relative error criterion or minimizing the largest relative error criterion, this paper points out that the improved Verhulst model parameter problem can be transformed to linear programming, that is, the parameters of the improving Verhulst model can be calculated by a linear programming method. Practical application shows that this method is feasible and effective, and has high forecasting accuracy over traditional method.