Tail Relation between Return and Volume in the US Stock Market: An Analysis Based on Extreme Value Theory

18 Pages Posted: 8 Jul 2016

See all articles by François Longin

François Longin

ESSEC Business School

Giovanni Pagliardi

BI Norwegian Business School

Date Written: July 5, 2016

Abstract

Using daily data of the S&P 500 index from 1950 to 2015, we investigate the relation between return and transaction volume in the statistical distribution tails associated with booms and crashes in the US stock market. We use extreme value theory (peaks-over-threshold method) to study the extreme dependence between the two variables. We show that the extreme correlation between return and volume decreases as we consider larger events in both the left and right distribution tails. From an economic viewpoint, this paper contributes to a better understanding of the activity of market participants during extreme events. Our empirical result is consistent with the economic explanation by Gennotte and Leland (1990) of extreme price movements based on misinterpretation of trades by market participants.

Keywords: extreme value theory, peaks-over-threshold method, return-volume dependence, stock market volatility, extreme correlation

JEL Classification: C58, G12

Suggested Citation

Longin, François and Pagliardi, Giovanni, Tail Relation between Return and Volume in the US Stock Market: An Analysis Based on Extreme Value Theory (July 5, 2016). Available at SSRN: https://ssrn.com/abstract=2805019 or http://dx.doi.org/10.2139/ssrn.2805019

François Longin (Contact Author)

ESSEC Business School ( email )

Avenue Bernard Hirsch
BP 105 Cergy Cedex, 95021
France

HOME PAGE: http://www.essec.edu/faculty/francois-longin

Giovanni Pagliardi

BI Norwegian Business School ( email )

Nydalsveien 37
Oslo, 0442
Norway

Register to save articles to
your library

Register

Paper statistics

Downloads
78
Abstract Views
548
rank
315,364
PlumX Metrics