数学建模中回归分析法.docVIP

本科毕业论文 题目名称： 数学建模中的回归分析法 学 院： 数学与统计学院 专业年级： 数学与应用数学2009级 （精算与风险管理） 学生姓名： 李 雨 函 班级学号： 200911030139 指导教师： 王 艺 霏 二O一三年五月二十四日 PAGE \* MERGEFORMAT PAGE \* MERGEFORMAT III 摘我们要 现实生活中, 由于客观事物内部规律的复杂性及人们认识程度的限制, 人们常搜集大量的数据, 基于数据的统计分析建立合乎机理规律的数学模型, 然后通过计算得到的模型结果来解释实际问题. 回归分析法是数学模型中常用解决问题的有效方法. 它是研究某个变量关于另一些变量的具体依赖关系的计算方法. 主要内容是从一组样本数据出发, 确定变量之间的数学关系式对这些关系式的可信程度进行各种统计检验, 并从影响某一特定变量的诸多变量中找出哪些变量的影响显著, 哪些不显著. 利用所求的关系式, 根据一个或几个变量的取值来预测或控制另一个特定变量的取值, 并给出这种预测或控制的精确程度. 本文介绍线性回归模型和非线性回归模型的概念、基本原理和应用步骤, 并最后通过实例分析介绍从数据出发建立、检验回归模型的步骤和模型结果中具体每个符号的实际意义. 结果表明, 在实际生活各个领域, 回归分析是很好的预测分析方法. 关键字: 回归分析; 线性回归模型; 非线性回归模型 Abstract In real life, the complexity of the internal law of things and awareness of the limits, people collected a large amount of data and based on the statistical analysis of data to set up mechanism model, and then through the calculated model results to explain the practical problems. Regression analysis is commonly used in mathematical model is the effective method to solve the problem. It is the study of one variable on other variables depend on the specific calculation method. The main content from a set of sample data, determine the mathematical relationship between the variables of the relation between the credible degree of various statistical tests, and from the influence of a particular variable variables to find out the influence of which variables significantly, which was not significant. The use of petitions, according to the value of one or several variables to predict or control the other of a particular variable values, and give the accurate predict or control. This paper introduces the concept of the linear regression model and nonlinear regression model, basic principle and application steps, and finally through the instance analysis is introduced from data set up, testing procedure and model of the regression model results in the practic