An empirical investigation of the rank correlation between different risk measures

Andreas Pfingsten, Peter Wagner and Carsten Wolferink

Abstract

ABSTRACT

A wealth of risk measures – for example, value-at-risk (VAR) – can be used to measure the risk of banks’ trading books. This gives rise to the question of whether the rankings produced by the various measures differ much in practical applications. To investigate this we analyze the rank correlations given by different risk measures using actual data from two trading books. In most cases we observe high values of Spearman’s coefficient, indicating that the choice of risk measure may not be too critical.