This thesis review the literature on Expected Shortfall (ES) backtesting methodologies and provides a comparative assessment of the main approaches, highlighting their respective strengths and weaknesses. The analysis is conducted for the S&P500 index, using 15 years of daily total return index data, covering the period from from July 1, 2011 to June 30, 2026. The Expected Shortfall is estimated using a range of parametric, semi-parametric, volatility-based models different models. The forecasting performance of these models is evaluated through Expected Shortfall procedures to compare their effectiveness to capture tail risk.
Questa tesi passa in rassegna la letteratura sulle metodologie di backtesting dell'Expected Shortfall (ES) e fornisce una valutazione comparativa dei principali approcci, evidenziandone i rispettivi punti di forza e di debolezza. L'analisi empirica è condotta sull'indice S&P 500, utilizzando 15 anni di total return index giornalieri, relativi al periodo compreso tra il 1/07/2011 e il 30/06/2026. L'Expected Shortfall è stimato mediante un insieme di modelli parametrici, semiparametrici e basati sulla volatilità. La qualità delle previsioni di tali modelli è valutata attraverso procedure di backtesting dell'Expected Shortfall, al fine di confrontarne l'efficacia nella misurazione del rischio di coda.
Backtesting expected shortfall models: a comparative empirical analysis
GRAVILI, COSIMO MARCO
2025/2026
Abstract
This thesis review the literature on Expected Shortfall (ES) backtesting methodologies and provides a comparative assessment of the main approaches, highlighting their respective strengths and weaknesses. The analysis is conducted for the S&P500 index, using 15 years of daily total return index data, covering the period from from July 1, 2011 to June 30, 2026. The Expected Shortfall is estimated using a range of parametric, semi-parametric, volatility-based models different models. The forecasting performance of these models is evaluated through Expected Shortfall procedures to compare their effectiveness to capture tail risk.| File | Dimensione | Formato | |
|---|---|---|---|
|
Tesi GRAVILI COSIMO MARCO.pdf
accesso aperto
Dimensione
3.68 MB
Formato
Adobe PDF
|
3.68 MB | Adobe PDF | Visualizza/Apri |
The text of this website © Università degli studi di Padova. Full Text are published under a non-exclusive license. Metadata are under a CC0 License
https://hdl.handle.net/20.500.12608/115047