A Test of General Asymmetric Dependence

Journal of Applied Econometrics, 2018, 33, 1026-1043.

34 Pages Posted: 11 May 2018 Last revised: 16 Nov 2023

See all articles by Lei Jiang

Lei Jiang

Tsinghua University

Esfandiar Maasoumi

Emory University

Jiening Pan

Nankai University

Ke Wu

Renmin University of China

Date Written: April 24, 2018

Abstract

We propose a modified mutual information measure to capture general asymmetric dependence between two random variables. Based on this measure, we propose a test of asymmetric dependence and examine its finite-sample performance. We show that our test has better power than competing tests with alternative dependence measures. Using the new test, we find significant asymmetric dependence in returns of commonly-used stock portfolios and the market return both in the U.S and other developed countries. Further, the dependence between developed country markets and the U.S. market is stronger when both markets are in a downturn.

Keywords: Asymmetric Dependence, Kullback-Leibler Relative Entropy, Exceedance Mutual Information

JEL Classification: C12, C15, C32, G12

Suggested Citation

Jiang, Lei and Maasoumi, Esfandiar Essie and Pan, Jiening and Wu, Ke, A Test of General Asymmetric Dependence (April 24, 2018). Journal of Applied Econometrics, 2018, 33, 1026-1043., Available at SSRN: https://ssrn.com/abstract=3164384

Lei Jiang

Tsinghua University ( email )

Beijing, 100084
China

Esfandiar Essie Maasoumi

Emory University ( email )

1602 Fishburne Drive
Atlanta, GA 30322
United States

HOME PAGE: http://economics.emory.edu/home/people/faculty/Maasoumiesfandiar_Home.html

Jiening Pan

Nankai University ( email )

38 Tongyan Road, Jinnan District
Tianjin, Tianjin 300350
China

Ke Wu (Contact Author)

Renmin University of China ( email )

59 Zhongguancun Street
Beijing, 100872
China

HOME PAGE: http://sf.ruc.edu.cn/info/1412/9666.htm

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
97
Abstract Views
1,040
Rank
489,322
PlumX Metrics