讲座主题：Measuring inequality for winners and losers:extended Lorenz curves and Gini indices for possibly negative variables

主讲嘉宾：贺天宇，天津大学马寅初经济学院助理教授

时间：2023年11月23日（周四）13:30-15:30

地点：澳门新莆京7906not沙河校区 二教108

主持人：苗壮 助理教授

点评人：苗壮 助理教授

主办：澳门新莆京7906not

致谢:  本讲座获得2023年澳门新莆京7906not专题学术讲座资助计划支持

讲座内容：

Commonly used inequality measures are not defined for variables that can potentially take negative values, even though income or other wealth measures in surveys can encompass populations with both "winners" and "losers." Several corrections have been proposed to address the issue of negative values, but these modified measures have primarily been employed as descriptive tools rather than as formal statistical inference methods. In this study, our focus is on a collection of extended inequality measures proposed by Bouezmarni (2020) within a comprehensive theoretical framework. We aim to provide nonparametric inference methods for these extended inequality measures, specifically including pointwise confidence intervals for the extended Lorenz shares, extended Gini indices, and uniform confidence bands for the extended Lorenz curves. To evaluate the performance of the proposed methods, extensive Monte Carlo simulations are conducted. Additionally, we explore the properties and potential applications of these measures, introduce an alternative Line of Equality, and establish the equivalence between signed and positive Lorenz curves. To demonstrate the practical significance of extended inequality measures, we conduct an in-depth analysis of the inequality of household financial income in Italy. Furthermore, we investigate the cross-sectional dispersion of US stock returns to illustrate the versatility of these measures as general dispersion indicators.

嘉宾简介

贺天宇，天津大学马寅初经济学院助理教授，加拿大麦吉尔大学经济学博士，师从Jean-Marie Dufour (世界计量经济学会会士，曾任Econometrica, Journal of Econometrics等期刊副主编)。主要研究方向为计量经济学和劳动经济学，关注不平等和贫困度量和统计检验，以及弱识别问题。目前，贺天宇与Dufour教授有三篇工作论文和两个进展中的项目。