Testing Methods to Reduce Noise in Financial Correlation Matrices

  • Per-Johan Andersson
  • Andreas Öberg
  • Thomas Guhr
Conference paper

4 Conclusions

As the two noise reduction methods are conceptually different, they also produce different results. Our preliminary studies cannot serve as a basis to make schematic suggestions as to which method ought to be preferred in which situation. This will always be difficult. But further and systematic studies extending the ones presented here might yield some guidelines.


Power Mapping Noise Reduction Random Matrix Correlation Matrice Portfolio Return 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Laloux L, Cizeau P, Bouchaud JP, Potters M (1999), Noise Dressing of Financial Correlation Matrices, Phys. Rev. Lett. 83:1467–1470CrossRefADSGoogle Scholar
  2. 2.
    Plerou V, Gopikrishnan P, Rosenow B, Amaral LAN, Stanley HE (1999), Universal and Nonuniversal Properties of Cross-Correlations in Financial Time Series, Phys. Rev. Lett. 83:1471–1474CrossRefADSGoogle Scholar
  3. 3.
    Gopikrishnan P, Rosenow B, Plerou V, Stanley HE (2001), Quantifying and Interpreting Collective Behavior in Financial Markets, Phys. Rev. E64:035106(R)ADSGoogle Scholar
  4. 4.
    Plerou V, Gopikrishnan P, Rosenow B, Amaral LAN, Guhr T, Stanley HE (2002), A Random Matrix Approach to Cross-Correlations in Financial Data, Phys. Rev. E65:066126ADSGoogle Scholar
  5. 5.
    Guhr T, Kälber B (2003), A New Method to Estimate the Noise in Financial Correlation Matrices, J. Phys. A36:3009–3032ADSGoogle Scholar
  6. 6. (2003), web downloadGoogle Scholar
  7. 7.
    Fama E, French K (2003), web downloadGoogle Scholar

Copyright information

© Springer-Verlag Tokyo 2006

Authors and Affiliations

  • Per-Johan Andersson
    • 1
  • Andreas Öberg
    • 1
  • Thomas Guhr
    • 1
  1. 1.Matematisk Fysik, LTHLunds UniversitetSweden

Personalised recommendations