Elicitability and identifiability of set-valued measures of systemic risk

by Tobias Fissler1, Jana Hlavinová2 and Birgit Rudloff3
1WU Vienna University of Economics and Business, Institute for Statistics and Mathematics, Welthandelsplatz 1, 1020 Vienna, Austria
(email: tobias.fissler@wu.ac.at)
2WU Vienna University of Economics and Business, Institute for Statistics and Mathematics, Welthandelsplatz 1, 1020 Vienna, Austria
(email: jana.hlavinova@wu.ac.at)
3WU Vienna University of Economics and Business, Institute for Statistics and Mathematics, Welthandelsplatz 1, 1020 Vienna, Austria
(email: birgit.rudloff@wu.ac.at)

Abstract

Identification and scoring functions are statistical tools to assess the calibration and the relative performance of risk measure estimates, e.g. in backtesting. A risk measure is called identifiable (elicitable) if it admits a strict identification function (strictly consistent scoring function). We consider measures of systemic risk introduced in Feinstein et al. (Measures of systemic risk. SIAM J. Financial Math. 8:672-708, 2017). Since these are set-valued, we work within the theoretical framework of Fissler et al. (Forecast evaluation of set-valued functionals. Preprint, 2020) for forecast evaluation of set-valued functionals. We construct oriented selective identification functions, which induce a mixture representation of (strictly) consistent scoring functions. Their applicability is demonstrated with a comprehensive simulation study.


Key words:

Consistent scoring functions, Diebold-Mariano tests, Forecast evaluation, $M$-estimation, Murphy diagrams
JEL Classification:  C52, G32
Mathematics Subject Classification (2010): 62F07, 62F10, 91B30, 91G70