基于残差分析测度修正的半参数统计推断模型的新疆发电量实证分析与检验  

An Empirical Analysis and Test of Power Generation in Xinjiang Based on the Semi-parametric Statistical Inference Model with Residual Correction

作　　者：袁婷[1] 刘淼[1] 

机构地区：[1]伊犁师范学院数学与统计学院,新疆伊宁835000

出　　处：《兰州文理学院学报（自然科学版）》2018年第1期28-33,共6页Journal of Lanzhou University of Arts and Science(Natural Sciences)

基　　金：新疆维吾尔自治区自然科学基金项目(2016D01C386)

摘　　要：在参数回归和非参数回归的基础上,通过非参数部分参数化处理的思想得到半参数模型,用半参数回归模型反映可知和未知信息,并建立基本预测模型,利用残差分布测度修正原理对预测模型的误差项进行了改进,最后将改进的半参数回归预测模型应用于新疆发电量预测.仿真结果表明,基于该方法的发电量预测效果显著.Based on the parameter regression non parametric regression,firstly a semi-parametric model is obtained by non-parametric part being treated as parametric in this paper.Secondly,using semiparametric regression model to reflect the known and unknown information,a basic prediction model is established.Thirdly,the error prediction is improved through residual correction principle.Lastly,the parameters of the improved regression prediction model are applied to the forecasting of power generation in Xinjiang.The simulation results show that this method has significant effect on the forecasting of electricity demand.

关 键 词：半参数 学生残差 正态性 参数化 

分 类 号：O211.67[理学—概率论与数理统计]