基于经验似然的单指标模型异方差诊断  

Empirical Likelihood Based Diagnostics for Heteroscedasticity in Single-index Model

作　　者：刘锋 王鹏飞 李春燕 康新梅 LIU Feng;WANG Peng-fei;LI Chun-yan;KANG Xin-mei(Department of Statistics, Chongqing University of Technology , Chongqing 400054, Chin)

机构地区：[1]重庆理工大学理学院,重庆400054

出　　处：《重庆工商大学学报（自然科学版）》2018年第3期1-9,共9页Journal of Chongqing Technology and Business University:Natural Science Edition

基　　金：国家自然科学基金项目资助(11471060)

摘　　要：研究了单指标模型的异方差诊断问题,首先采用经验似然的方法对模型误差项进行异方差检验,构造了纠偏经验似然比检验;然后得到了经验似然比统计量,并证得其为渐进卡方分布;最后的数值模拟结果表明:该检验方法具有理想的检验功效。We considered the diagnostics for heteroscedasticity in single-index model. Firstly,we applied the empirical likelihood method to test the heteroscedasticity for errors of single-index model,and constructed the biascorrected empirical likelihood ratio test. Then we obtained the ratio statistic of empirical likelihood and derived the asymptotic Chi square distribution of the statistic. Finally,simulation results indicate that the method performs well.

关 键 词：异方差性 单指标模型 经验似然比 

分 类 号：O212.7[理学—概率论与数理统计]