Author(s): Xia-yan LI 1, Jun-qing YUAN 2, 1 Department of Statistics and Finance, University of Science and Technology of China, Hefei 230026, China 2 School of Science, Zhejiang University of Technology, Hangzhou 310023, China
Pages: 265-274
Year: 2012 Issue:  2
Journal: Acta Mathematicae Applicatae Sinica
Keyword:  confidence interval;  empirical likelihood;  quantile;  missing response;  regression imputation;
Abstract: Empirical likelihood is a nonparametric method for constructing confidence intervals and tests,notably in enabling the shape of a confidence region determined by the sample data.This paper presents a new version of the empirical likelihood method for quantiles under kernel regression imputation to adapt missing response data.It eliminates the need to solve nonlinear equations,and it is easy to apply.We also consider exponential empirical likelihood as an alternative method.Numerical results are presented to compare our method with others.