计算机工程与应用 ›› 2009, Vol. 45 ›› Issue (33): 42-44.DOI: 10.3778/j.issn.1002-8331.2009.33.014

• 研究、探讨 • 上一篇    下一篇

基于粒子群算法的Logistic回归模型参数估计

刘锦萍1,2,郁金祥2   

  1. 1.华东师范大学 计算机科学系,上海 200062
    2.嘉兴学院 数学与信息工程学院,浙江 嘉兴 314001
  • 收稿日期:2009-02-25 修回日期:2009-04-20 出版日期:2009-11-21 发布日期:2009-11-21
  • 通讯作者: 刘锦萍

Parameter estimation method of logistic regression models based on particle swarm optimization algorithm

LIU Jin-ping1,2,YU Jin-xiang2   

  1. 1.Department of Computer Science,East China Normal University,Shanghai 200062,China
    2.College of Mathematics,Jiaxing University,Jiaxing,Zhejiang 314001,China
  • Received:2009-02-25 Revised:2009-04-20 Online:2009-11-21 Published:2009-11-21
  • Contact: LIU Jin-ping

摘要: 针对Logistic回归模型中的参数估计计算复杂难题,提出一种基于粒子群优化算法(PSO)的估计方法。以最大似然准则作为粒子群优化算法的适应度函数,建立了Logistic回归模型中的参数估算模型。数值仿真分析表明,粒子群优化算法可以更精确地计算出相关参数。

关键词: 粒子群优化算法, 参数估计, Logistic回归模型, 最大似然估计

Abstract: In order to solve the computing complex problems of the parameter estimation to the logistic regression models,a novel method to estimate parameter is presented based on particle swarm optimization algorithm.Maximum likelihood estimation is adopted to be fitness function for the optimization problem.Thus the model of computing parameter to the logistic regression models is set up.The numerical simulation results show that PSO algorithm can be used to calculate the parameters of the logistic regression models.

Key words: particle swarm optimization, parameter estimation, logistic regression models, maximum likelihood estimation

中图分类号: