使用怀特检验判断生物量模型的异方差性  

White Test for Heteroskedasticity of Biomass Model

作　　者：申屠惠良[1] 

机构地区：[1]国家林业局华东林业调查规划设计院,浙江杭州310019

出　　处：《浙江林业科技》2012年第3期43-45,共3页Journal of Zhejiang Forestry Science and Technology

摘　　要：为了在生物量建模过程中得到回归模型的最优估计,针对回归模型存在的异方差性,提出用怀特检验方法来定量分析模型,再结合残差分布图来辅助判断,并应用怀特检验方法和残差分布图实例分析了普通最小二乘法拟合栎类生物量模型结果存在异方差性,建议采用加权最小二乘法拟合栎类生物量模型。In order to have the optimal estimation during regression model for biomass, White test was recommended to quantitative analyze model, associated by residuals distribution. Application of White test and residuals was conducted on analysis of biomass model for Quercus L. fitted by ordinary least squares, the result showed that there had heteroskedasticity. Therefore, weighted least squares were recommended to fit biomass model for Quercus L.

关 键 词：生物量 模型 怀特检验 异方差性 

分 类 号：S718.556[农业科学—林学]