The Fellowship of LIBOR: A Study of Spurious Interbank Correlations by the Method of Wigner-Ville Function

Abstract

The manipulation of the LIBOR by a group of banks became one of the major blows to the remaining confidence in the finance industry (e.g. Department of Justice, 2012). Yet, despite an enormous amount of popular literature on the subject, rigorous time-series studies are few. In my paper, I discuss the following hypothesis. If, as we should assume for the statistical null, the quotes, which were submitted by the banks were true, the deviations of the submitted quotes from the LIBOR must have been entirely random because they were determined by idiosyncratic conditions of the member banks. This hypothesis is amenable to statistical verification.Serial correlations of the rates, which cannot be explained by the differences in credit quality of the banks or the domicile Governments, are subjected to correlation tests. A new econometric method — the analysis of the vector Wigner-Ville function borrowed from the quantum physics and signal processing — is used and explained for the statistical interpretation of regression residuals.