摘要:Measuring economic inequality is a significant and meaningful topic in our social system. The Gini index and Pietra ratio are used by many people, but limited to reflecting the sampling distribution. In this paper, we studied the interval estimates with another measure called the lower-mean ratio u, which was introduced by Elteto and Frigyes (1968). By using jackknife empirical likelihood (JEL), adjusted jackknife empirical likelihood (AJEL), mean jackknife empirical likelihood (MJEL), mean adjusted jackknife empirical likelihood (MAJEL), and adjusted mean jackknife empirical likelihood (AMJEL) methods, we proposed the interval estimator for u. In the following simulation study, we made a comparison for these methods under different distributions in terms of the coverage probability and the average confidence interval length. The results indicate that MAJEL performs best among these methods for small sample sizes of skewed distribution. For a small sample size of normal distribution, both JEL and MJEL show better performance than the other methods but MJEL is relatively time-consuming. All methods exhibit good performance for the large sample size. The two real data set analyses further illustrate the proposed methods, and the results are consistent with those in the simulation study.
简介:黄磊，博士，2015年毕业于新加坡国立大学，现任职于西南交通大学数学学院，副教授，硕士生导师，研究方向包括半参数时间序列模型、金融统计分析、医学生物统计。已发表论文二十篇，其中包括SCI期刊论文10余篇，部分论文发表在Annals of Statistics, Statistical Methods in Medical Research, Statistics in Medicine, Computational Statistics and Data Analysis, Journal of Statistical Computation and Simulation, Enterprise Information Systems等期刊上。主持一项国家自科青年项目和一项省级科研项目，参与自科面上项目、青年项目各一项，参与教育部人文社科项目两项。2017年获中国留学基金委(CSC)访问学者资助项目。