CFE 2020: Start Registration
View Submission - CMStatistics
Title: Reduce the computation in jackknife empirical likelihood for comparing two correlated Gini indices Authors:  Kangni Alemdjrodo - Georgia State University (United States)
Yichuan Zhao - Georgia State University (United States) [presenting]
Abstract: The Gini index has been widely used as a measure of income (or wealth) inequality in social sciences. To construct a confidence interval for the difference of two Gini indices from the paired samples, a profile jackknife empirical likelihood after maximization over a nuisance parameter has been used, and a Wilks' theorem has been established. However, profiling could be very expensive. We propose an alternative approach of the jackknife empirical likelihood method to reduce the computational cost. We also investigate the adjusted jackknife empirical likelihood and the bootstrap-calibrated jackknife empirical likelihood to improve coverage accuracy for small samples. Simulations show that the proposed methods perform better than the previous methods in terms of coverage accuracy and computational time. Two real data applications proved that the proposed methods work perfectly in practice.