Estimation of GM (1, 1) model parameter usually adopts the least square criterion, but test of model precision often USES average relative error criterion.
估计GM(1,1)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常采用平均相对误差。
But for case of measured correlation sequence the whole sequence may be used to reduce the effect of error on model parameter estimation.
但是对实测的相关序列，我们可以利用相关序列的全部来减小误差对参数估计的影响。
The results of simulated and real data procession show that the proposed method favorably compares to other ones as to the parameter estimation error and its standard deviation.
仿真和实际数据处理的结果表明，该方法在参数估计误差和标准差方面明显优于其它算法。
应用推荐