广西师范大学学报（自然科学版） ›› 2013, Vol. 31 ›› Issue (4): 60-65.

• • 上一篇    下一篇

基于垂直密度表示的经验欧氏拟合优度检验

张新成1,2, 张军舰1, 詹欢1   

  1. 1.广西师范大学数学科学学院,广西桂林541004;
    2.开封大学信息工程学院,河南开封475004
  • 收稿日期:2013-10-09 出版日期:2013-12-20 发布日期:2018-11-26
  • 通讯作者: 张军舰(1973—),男,河南内乡人,广西师范大学教授,博士。E-mail:jjzhang@gxnu.edu.cn
  • 基金资助:
    国家自然科学基金资助项目(11261009);国家社会科学基金资助项目(10CTJ004);广西自然科学基金资助项目(2012GXNSFAA053004)

A Goodness-of-fit Test Based on Empirical Euclidean Likelihood and Vertical Density Representation

ZHANG Xin-cheng1,2, ZHANG Jun-jian1, ZHAN Huan1   

  1. 1.College of Mathematical Sciences,Guangxi Normal University,Guilin Guangxi 541004,China;
    2.College of Information Technology,Kaifeng University,Kaifeng Henan 475004,China
  • Received:2013-10-09 Online:2013-12-20 Published:2018-11-26

摘要： 本文利用经验欧氏似然方法和垂直密度表示(VDR)构造一类新的拟合优度检验,并讨论在简单零假设下,检验统计量的极限分布;然后利用极大似然估计所得的参数估计量构造复合零假设下的检验函数,并讨论其极限性质;最后把所得的检验与传统变量分组方式所得到的检验进行功效模拟比较。模拟结果显示:使用VDR分组方式求得的经验欧氏似然检验在大多数情况下都比传统变量分组方式得到的检验的功效要高,在应用上更具有推广价值。

关键词: 拟合优度检验, 经验欧氏似然, 垂直密度表示

Abstract: A goodness of fit test was constructed by means of empirical Euclidean likelihood and vertical density representation (VDR),and the limit null distribution of the test statistics was derived.Then,the parameters were estimated by maximum likelihood estimate (MLE) under the composite null hypothesis.Subsequently,the corresponding test statistics was constructed and its limit null distribution was given.Finally,the new tests were compared with the traditional chi-square test by simulations.Simulation results show that the new tests are more powerful and have favorable application and potential prospect.

Key words: goodness-of-fit, empirical Euclidean likelihood, vertical density representation

中图分类号: 

  • O212.1
[1] 张军舰.非参数似然比拟合优度检验[R].北京:北京工业大学,2008.
[2] 杨振海,程维虎,张军舰.拟合优度检验[M].北京:科学出版社,2011.
[3] OWEN A B.Empirical likelihood ratio confidence intervals for a single functional[J].Biometrika,1988,75(2):237-249.
[4] OWEN A B.Empirical likelihood[M].Boca Raton:Chapman and Hall/CRC,2001.
[5] 罗旭.半参数模型的经验欧氏似然估计的大样本性质[J].应用概率统计,1994,10(4):344-352.
[6] 张军舰,詹欢,晏振.基于经验欧氏似然的拟合优度检验[J].广西师范大学学报:自然科学版,2012,30(3):30-35.
[7] TROUTT M D.Vertical density representation and a further remark on Box-Muller method[J].Statistics,1993,24(1):81-83.
[8] TROUTT M D,PANG W K,HOU S H.Vertical density representation and its applications[M].Hackensack,NJ:World Scientific Publishing Co Pte Ltd,2004.
[1] 张军舰, 詹欢, 晏振. 基于经验欧氏似然的拟合优度检验[J]. 广西师范大学学报（自然科学版）, 2012, 30(3): 30-35.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 广西师范大学学报（自然科学版）编辑部
地址：广西桂林市三里店育才路15号　邮编：541004
电话：0773-5857325　E-mail: gxsdzkb@mailbox.gxnu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发