Volatility Forecast Evaluation and Comparison Using Imperfect Volatility Proxies

By Andrew J. Patton, Incomplete. 2005

74 citations recorded by the source corpus.

Subfields: Economics and Econometrics, Finance

View Paper: https://www.semanticscholar.org/paper/ba9e807b8218b0fdd28926f739cec8b7a17877dc

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Economics and Econometrics

In Finance

Citations in the corpus

Structural breaks and GARCH models of exchange rate volatility (2008, methodology): “30 Subject to a minimum window length requirement, Pesaran and Timmermann (2007) consider combining the forecasts from individual models estimated using all possible window sizes.”
Sequential Conditional Correlations: Inference and Evaluation (2009, unknown): “…1 T − K + 1 T −K+1∑ t=1 [ M∑ r=1 M∑ c=r+1 ∣∣∣∣Υ̂ (K) r,c,t − R̂(K)r,c,t ∣∣∣∣ ] While in the MGARCH literature the MAD tends to be preferred to the MSE on the grounds of robustness, Patton (2008) showed that using the MAD can lead to the conclusion that the perfect forecast is inferior to a biased…”
Forecasting Volatility Using High-Frequency Data (2011, background): “Patton (2008) generalized this result by providing necessary and sufficient conditions to ensure that the true preordering and the approximate preordering for a univariate loss function are equivalent.”
Realized Volatility: A Review (2008, methodology): “Andersen and Bollerslev (1998), Hansen and Lunde (2005a), and Patton (2005) used this new volatility measure to evaluate the out-of-sample forecasting performance of GARCH models.1 As volatility becomes “observable,” it can be modeled directly, rather than being treated as a latent variable.”
Forecasting Stock Market Volatility with Regime-Switching GARCH Models (2005, background): “In particular, at shorter horizons (until one week) the MRS-GARCH-N always fares better than the bench19However, as shown in Patton (2005), the HMSE loss does not imply that the conditional variance is the optimal forecast.”
Realising the future: forecasting with high frequency based volatility (HEAVY) models (2010, methodology): “This loss function has been shown to be robust to certain types of noise in the proxy in Patton (2009) and Patton and Sheppard (2009a).”
Variation, jumps, market frictions and high frequency data in financial econometrics (2005, unknown): “Hansen and Lunde (2005a) and Patton (2005) have focused on the delicate implications of the use of different loss functions to discriminate between competing forecasting models, where the object of the forecasting is V̂i or a function of it.”
Realized Variance and Market Microstructure Noise (2006, background): “High-frequency–based quantities are also useful in the context of forecasting (see Andersen, Bollerslev, and Meddahi 2004; Ghysels, Santa-Clara, and Valkanov 2006) and the evaluation and comparison of volatility models (see Andersen and Bollerslev 1998; Hansen, Lunde, and Nason 2003; Hansen and Lund”