Robust Risk Measures in Real Time Settings

• Antragsteller: Professor Dr. Winfried Franz Xaver Pohlmeier
• Fachliche Zuordnung: Statistik und Ökonometrie
• Förderung: Förderung von 2010 bis 2014
• Projektkennung: Deutsche Forschungsgemeinschaft (DFG) - Projektnummer 178371044

• Erstellungsjahr: 2019

Zusammenfassung der Projektergebnisse

This research project contributed to the improved estimation of downsided financial risk measures. The improvements include the use of high frequency data, the optimal combination of alternative risk measures and by joint estimation and testing of of the risk measures accounting for elicitability. In several empirical applications it was shown, that the conventional approaches, which still are in use by financial institutions are far from being optimal. Financial risk are not only inherent to financial markets, they are also the result of the use of mediocre tools to measure them. The project results point out that proper risk measurement in the future should make heavy use of the plethora of financial data and econometric models by machine learning techniques and appropriate sampling techniques.

Projektbezogene Publikationen (Auswahl)

• (2012): “Improving the value at risk forecasts: Theory and evidence from the financial crisis,” Journal of Economic Dynamics and Control, 36, 1212–1228
  Halbleib, R. & W. Pohlmeier
  
• (2013): “An MCMC Approach to Multivariate Density Forecasting: An Application to Liquidity,” CoFE Working Paper (May 5, 2013), University of Konstanz
  Krueger, F. & I. Nolte
  
• Three Essays on Robust Optimization of Efficient Portfolios, Ph.d. thesis, University of Konstanz
  Liu, H.
  
• (2014): “Estimating GARCH-type models with symmetric stable innovations: Indirect inference versus maximum likelihood,” Computational Statistics & Data Analysis, 76, 158 – 171
  Calzolari, G., R. Halbleib, & A. Parrini
  
• (2014): “Forecasting Covariance Matrices: A Mixed Approach,” Journal of Financial Econometrics, 14 (2), 383–417
  Halbleib, R. & V. Voev
  
• (2017): Messen und Verstehen von Finanzrisiken – Eine Perspektive der Ökonometrie, chap. 10, Springer Fachmedien Wiesbaden, Wiesbaden, pp. 135–149
  Halbleib, R.
  
• (2017): Three Essays on Improving Financial RiskEstimation, Forecasting and Backtesting, Ph.d. thesis, University of Konstanz
  Bayer, S.
  
• (2017): “A Latent Factor Model for Forecasting Realized Volatilities,” GSDS Working Paper No. 2017-14, University of Konstanz
  Calzolari, G., R. Halbleib, & A. Zagidullina
  
• (2018): Three Essays on Estimation, Forecastingand Evaluation of Financial Risk, Ph.d. thesis, University of Konstanz
  Dimitriadis, T.
  
• (2018): “Combining Value-at-Risk forecasts using penalized quantile regressions,” Econometrics and Statistics, 8, 56 – 77
  Bayer, S.
  
• (2018): “Estimating stable latent factor models by indirect inference,” Journal of Econometrics, 205 (1), 280 – 301
  Calzolari, G. & R. Halbleib
  
• (2018): “How Informative Is High-Frequency Data for Tail Risk Estimation and Forecasting? An Intrinsic Time Perspective,” GSDS Working Paper No. 2018-04, University of Konstanz
  Dimitriadis, T. & . Halbleib, Roxana
  
• (2019): Three Essays on Covariance Matrix Estimation and Factor Models in High Dimensions, Ph.d. thesis, University of Konstanz
  Zagidullina, A.
  
• (2019): “A joint quantile and expected shortfall regression framework,” Electron. J. Statist., 13 (1), 1823–1871
  Dimitriadis, T. & S. Bayer
  
• (2019): “Regression Based Expected Shortfall Backtesting,” Tech. rep.
  Bayer, S. & T. Dimitriadis