Gompertz曲线参数估计新方法(英文)  

A New Method of Parameter-Estimation for the Gompertz Curve

作　　者：胡晓华[1] 虞敏[2] 吉承儒[2] 

机构地区：[1]海南师范大学数学与统计学院,海口571158 [2]海南师范大学教务处,海口571158

出　　处：《数学理论与应用》2011年第2期55-60,共6页Mathematical Theory and Applications

摘　　要：我们提出了一种估计Gompertz曲线参数的新方法。通过研究产生Gompertz曲线的Gompertz微分方程,利用微分与差分的基本原理,借助多元回归方法,给定显著性水平α,在置信水平1-α下,估计出Gomper-tz曲线的参数。应用该结果研究中国1994年至2007年的汽车年销售数据,获得相应的预测数据和2008的预测值(1090万辆)。MAPE=5.58<10,显示模型有预测精度较高。We propose a new method of parameters estimation for Gomportz Curve. research Gompertz differential equation which creates Gompertz curve, by making use of the basic principle of differential and difference, given the α significance level, estimate parameters of Gompertz curve at the 1 -α confidence level via multi - regression, apply this result to study the China＇s car annual sales data from 1994 to 2007 , to obtain corresponding forecast data, and obtain forecast value at 2008 ,or 1090 ten thousand of cars. MAPE = 5.58 〈 10, it shows that the model has a higher prediction accuracy.

关 键 词：Gompertz曲线 微分与差分 多元回归 参数估计 

分 类 号：O212.1[理学—概率论与数理统计]