Cointegration in Finance: An Application to Index Tracking

53 Pages Posted: 11 Apr 2010

See all articles by Thomas Andreas Maurer

Thomas Andreas Maurer

The University of Hong Kong; Washington University in St. Louis - John M. Olin Business School; London School of Economics & Political Science (LSE)

Date Written: July 9, 2008

Abstract

The purpose of this paper is to construct and test two different index tracking strategies - one based upon cointegration analysis of the price processes of assets (CIT strategy), and the other based on a market equilibrium and continuous time portfolio optimisation approach (MIT strategy). Within a broad empirical analysis it is found that both tracking strategies are able to track an index (FTSE100, DJ Industrial, DJ Composite Average) accurately, even if only a relatively small subset of constituent stocks is used. Thereby, it is also suggested that (particularly in the British stock market) the CIT strategy is preferred since there is some (out of sample) evidence indicating that log-price spreads between index and CIT tracking portfolio follow a stationary process. Moreover, regarding the attempt to perform simple enhanced indexation, no empirical evidence was found that would suggest that either of the two tracking strategies was suitable for such an approach.

Keywords: index tracking, enhanced indexation, cointegration, portfolio optimization, tracking error minimization

Suggested Citation

Maurer, Thomas Andreas, Cointegration in Finance: An Application to Index Tracking (July 9, 2008). Available at SSRN: https://ssrn.com/abstract=1586997 or http://dx.doi.org/10.2139/ssrn.1586997

Thomas Andreas Maurer (Contact Author)

The University of Hong Kong ( email )

Pokfulam Road
Hong Kong, Pokfulam HK
Hong Kong

Washington University in St. Louis - John M. Olin Business School ( email )

One Brookings Drive
Campus Box 1133
St. Louis, MO 63130-4899
United States

London School of Economics & Political Science (LSE) ( email )

Houghton Street
London, WC2A 2AE
United Kingdom