论文部分内容阅读
以加权回归估计方法为核心 ,对林业上常用模型的异方差性进行了研究 ,提出了能彻底消除异方差的最佳权函数。并对模型的评价指标进行了探讨 ,提出了评价通用性回归模型的 3大指标 ,并分析了加权回归估计与这些评价指标之间的关系。最后对样本资料的收集进行了讨论 ,提出了收集建模样本应遵循的基本原则。
Taking the weighted regression estimation method as the core, the heteroscedasticity of the commonly used models in forestry is studied, and the optimal weight function that can completely eliminate heteroscedasticity is proposed. The evaluation index of the model is also discussed. Three indexes for evaluating the universal regression model are proposed, and the relationship between the weighted regression estimation and these evaluation indexes is analyzed. Finally, the collection of sample data was discussed, and the basic principles that should be followed in collecting the sample were put forward.