copula回归函数和方向相依-概率论与数理统计专业毕业论文.docx

西南交通大学硕士研究生学位论文 第H页
Abstr act
Depedence is an important part in probability and the used measure are Pearson coralation Kendal王’Sz,Spearman’S P, But they are all numbers,they can’t reflect the dependence relation beteen the。random variables exactly,In dependence modeling such as regression,one attempts to provide a functional form that will summarize the relationship beteen response and type of functional relationship could depend on the marginal beohaviors or their joint the second chapter,we will look at a way of
separating these behaviors。Wc will reflect the relation by using Copula
regression functions.
In chapter three,under the assumption of linear relationship beteen tWO variables we provide alternative simple method of proving the existing connecting correlation coefficient with those of skewness of response and explanatory variables。Further we have given a relationship between correlation coefficient and coefficient of kurtosis of response and explanatory variables.
In chapter four,we define and study the concept of directional dependence in bivariate regression setting by using consider two case of directional磊epende纛ee:o鑫e originating from marginals and the other originating from joint behavior of also generalize and clarify the result given by chapter three。we also introduce a measure that can be employed for both types of directional dependence and provide a detaile look for the linear also introduce an additional face of tortel ation.
Key words: Copula,dependence,regression function,directional dependence
西南交通大学曲南父遗大罕学位论文版权使用授权书
本学位论文作者完全了解学校有关保留、使用学位论文的规定,同意学校保留并向国家有关部门或机构送交论文的复印件和电子版,允许论文被查阅和借阅。本人授权西南交通大学可以将本论文的全部或部分内容编入有关数据库进行检索,可以采用影印、缩印或扫描等复印手段保存和汇编本学位论文。
本学位论文属于
,在 年解密后适用本授权书;
,使用本授权书。
(请在以上方框内打“√")
嚣专霈乒芦觋日期:伊o 矿 ,一 1{/ 指导老师签名:彳唧蕴
cJ·J·训 日期:咖∥.厂、谚7
西南交通大学学位论文创新性声明
本人郑重声明:所呈交的学位论文,是在导师指导下独立进行研究工作所得的成果。除文中已经注明引用的内容外,本论文不包含任何其他个人或集体己经发表或撰写过的研究成果。对本