符号多边形双变量回归模型研究

Study on Bivariate Regression Model of Symbolic Polygon

文章以符号多边形数据为研究对象,阐述将海量数据打包为符号多边形数据的具体过程,定义了符号多边形变量,给出了符号多边形变量的描述统计量。在此基础上,建立符号多边形双变量的广义线性回归模型。使用极大似然估计方法,对所建立的模型进行参数估计,蒙特卡洛模拟发现所提出的模型在多边形的中心和半径相关时有良好的表现。将模型应用于分析篮球职业联赛的团体得分与对手得分、上场时间、投球次数、个人得分和球员效率指数的关系研究中,弥补了多边形线性回归模型的不足。

Taking symbolic polygon data as the research object,this paper expounds the concrete process of packaging massive data into symbolic polygon data,defines the symbolic polygon variable,and gives the descriptive statistics of the symbolic polygon variable.On this basis is,the bivariate generalized linear regression model of symbolic polygonconstructed.This paper uses the maximum likelihood estimation method to estimate the parameters of the model.Monte Carlo simulation shows that the proposed model performs well when the center and radius of polygons are correlated.The model is applied to analyze the relationship between team score and opponents’score,playing time,shooting times,individual score and player efficiency index in professional basketball league,which makes up for the deficiency of polygon linear regression model.