Realized Mixed-Frequency Factor Models for Vast Dimensional Covariance Estimation

45 Pages Posted: 24 Oct 2012

See all articles by Karim Bannouh

Karim Bannouh

NN Investment Partners

Martin Martens

Erasmus University Rotterdam (EUR); Robeco Asset Management

Roel C. A. Oomen

Deutsche Bank AG (London); London School of Economics & Political Science (LSE) - Department of Statistics

Dick J. C. van Dijk

Erasmus University Rotterdam - Erasmus School of Economics - Econometric Institute; ERIM

Date Written: October 23, 2012

Abstract

We introduce a Mixed-Frequency Factor Model (MFFM) to estimate vast dimensional covari- ance matrices of asset returns. The MFFM uses high-frequency (intraday) data to estimate factor (co)variances and idiosyncratic risk and low-frequency (daily) data to estimate the factor loadings. We propose the use of highly liquid assets such as exchange traded funds (ETFs) as factors. Prices for these contracts are observed essentially free of microstructure noise at high frequencies, allowing us to obtain precise estimates of the factor covariances. The factor loadings instead are estimated from daily data to avoid biases due to market microstructure effects such as the relative illiquidity of individual stocks and non-synchronicity between the returns on factors and stocks. Our theoretical, simulation and empirical results illustrate that the performance of the MFFM is excellent, both compared to conventional factor models based solely on low-frequency data and to popular realized covariance estimators based on high-frequency data.

Keywords: factor models, high-frequency data, realized covariance, microstructure noise, non-synchronous trading

JEL Classification: G3, G11

Suggested Citation

Bannouh, Karim and Martens, Martin P.E. and Oomen, Roel C.A. and van Dijk, Dick J.C., Realized Mixed-Frequency Factor Models for Vast Dimensional Covariance Estimation (October 23, 2012). ERIM Report Series Reference No. ERS-2012-017-F&A. Available at SSRN: https://ssrn.com/abstract=2166179

Karim Bannouh (Contact Author)

NN Investment Partners ( email )

Schenkkade 65
The Hague, 2595 AS
Netherlands

Martin P.E. Martens

Erasmus University Rotterdam (EUR) ( email )

P.O. Box 1738
3000 DR Rotterdam
Netherlands
+31 10 408 1253 (Phone)
+31 10 408 9162 (Fax)

Robeco Asset Management ( email )

Rotterdam, 3011 AG
Netherlands

Roel C.A. Oomen

Deutsche Bank AG (London) ( email )

Winchester House
1 Great Winchester Street
London, EC2N 2DB
United Kingdom

London School of Economics & Political Science (LSE) - Department of Statistics ( email )

Houghton Street
London, England WC2A 2AE
United Kingdom

Dick J.C. Van Dijk

Erasmus University Rotterdam - Erasmus School of Economics - Econometric Institute

P.O. Box 1738
3000 DR Rotterdam
Netherlands

ERIM ( email )

P.O. Box 1738
3000 DR Rotterdam
Netherlands
+31 10 408 1263 (Phone)
+31 10 4089162 (Fax)

HOME PAGE: http://people.few.eur.nl/djvandijk

Register to save articles to
your library

Register

Paper statistics

Downloads
238
Abstract Views
1,265
rank
128,572
PlumX Metrics