Acknowledgements
CARISMA and Leela Mitra gratefully acknowledge the financial sponsorship provided by RavenPack International S.L. RavenPack also supplied the news sentiment data used in this study (see the appendix for further details). The authors would also like to express their gratitude to Editor-in-chief Michael Dempster and an anonymous referee for their assistance during the preparation of this article.
Notes
¶Visiting professor at CARISMA.
†The computational experiments are carried out using the component assets of the Eurostoxx 50, so the number of time periods T > N number of assets and we are able to carry out a principal component analysis on the N × T data set thereby avoiding the problem of the matrix becoming singular.