Forecasting multidimensional tail risk at short and long horizons

Evarist Stoja, Arnold Polanski

Research output: Contribution to journalArticle (Academic Journal)peer-review

6 Citations (Scopus)
157 Downloads (Pure)


We define Multidimensional Value at Risk (MVaR) as a natural generalization of VaR. This generalization makes possible a number of important applications. For example, many techniques developed for VaR can be applied directly to MVaR. As an illustration, we employ VaR forecasting and evaluation techniques. One of our forecasting models builds on the progress made in the volatility literature and decomposes MVaR into long-term trend and short-term cycle components. We compute short- and long-term MVaR forecasts for several multidimensional time series and discuss their (un)conditional accuracy.
Original languageEnglish
Pages (from-to)958-969
Number of pages12
JournalInternational Journal of Forecasting
Issue number4
Early online date31 Jul 2017
Publication statusPublished - 1 Oct 2017

Structured keywords

  • AF Financial Markets


  • Multidimensional Risk
  • Multidimensional Value at Risk
  • Two-factor decomposition
  • Long horizon forecasting


Dive into the research topics of 'Forecasting multidimensional tail risk at short and long horizons'. Together they form a unique fingerprint.

Cite this