It's all about volatility of volatility: Evidence from a two-factor stochastic volatility model

Grassi, Stefano; Magistris, Paolo Santucci de

doi:10.1016/j.jempfin.2014.11.007

Cited by 15 publications

(7 citation statements)

References 69 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To give better economic meaning to those factors, we therefore extract one common factor from each group. 7 See http://www.policyuncertainty.com 8 Note that, one could choose values for  and  based on the forecast performance as in Grassi and Santucci de Magistris (2013), but this would bias our results in favour of DMA, and thus is not a valid procedure for out-ofsample forecasting (Koop and Korobilis, 2011). Alternatively, when forecasting at time  , we could consider a grid of values for  and , and select the value which yielded the highest value for the marginal likelihood or an information criterion, which essentially amounts to treating  and  as unknown parameters.…”

Section: Resultsmentioning

confidence: 99%

Forecasting the price of gold using dynamic model averaging

Aye

Gupta

Hammoudeh

et al. 2015

International Review of Financial Analysis

113

View full text Add to dashboard Cite

We develop several models to examine possible predictors of the return of gold, which embrace six global factors (business cycle, nominal, interest rate, commodity, exchange rate and stock price) extracted from a recursive principal component analysis (PCA) and two uncertainty and stress indices (the Kansas City Fed's financial stress index and the U.S. Economic policy uncertainty index). Specifically, by comparing alternative predictive models, we show that the dynamic model averaging (DMA) and dynamic model selection (DMS) models outperform linear models (such as the random walk) as well as the Bayesian model averaging (BMA) model. The DMS is the best predictive model overall across all forecast horizons. Generally, all the predictors show strong predictive power at one time or another though at varying magnitudes, while the exchange rate factor and the Kansas City Fed's financial stress index appear to be strong at almost all horizons and sub-periods. However, the forecasting prowess of the exchange rate is supreme. JEL Classification codes: C11, C53, F37, F47, Q02 Abstract We develop several models to examine possible predictors of the return of gold, which embrace six global factors (business cycle, nominal, interest rate, commodity, exchange rate and stock price) extracted from a recursive principal component analysis (PCA) and two uncertainty and stress indices (the Kansas CityFed's financial stress index and the U.S. Economic policy uncertainty index). Specifically, by comparing alternative predictive models, we show that the dynamic model averaging (DMA) and dynamic model selection (DMS) models outperform linear models (such as the random walk) as well as the Bayesian model averaging (BMA) model. The DMS is the best predictive model overall across all forecast horizons.Generally, all the predictors show strong predictive power at one time or another though at varying magnitudes, while the exchange rate factor and the Kansas City Fed's financial stress index appear to be strong at almost all horizons and sub-periods. However, the forecasting prowess of the exchange rate is supreme.JEL Classification codes: C11, C53, F37, F47, Q02

show abstract

Section: Resultsmentioning

confidence: 99%

Forecasting the price of gold using dynamic model averaging

Aye

Gupta

Hammoudeh

et al. 2015

International Review of Financial Analysis

113

View full text Add to dashboard Cite

show abstract

“…Wang, Kirby, and Clark () showed the relation between volatility of volatility and variation of equity risk premium. Grassi and Magistris () considered the change of RVs related to the change in stochastic volatility. Some recent studies revealed that this volatility clustering has asymmetry.…”

Section: Forecast Mean Squared Error and Forecast Standard Errormentioning

confidence: 99%

Forecasts for leverage heterogeneous autoregressive models with jumps and other covariates

Choi

Shin

2018

Journal of Forecasting

View full text Add to dashboard Cite

For leverage heterogeneous autoregressive (LHAR) models with jumps and other covariates, called LHARX models, multistep forecasts are derived. Some optimal properties of forecasts in terms of conditional volatilities are discussed, which tells us to model conditional volatility for return but not for the LHARX regression error and other covariates. Forecast standard errors are constructed for which we need to model conditional volatilities both for return and for LHAR regression error and other blue covariates. The proposed methods are well illustrated by forecast analysis for the realized volatilities of the US stock price indexes: the S&P 500, the NASDAQ, the DJIA, and the RUSSELL indexes.

show abstract

“…n = 4680. The choice of the sample period is motivated by the evidence of parameter instability for the TFSV model during the sub-prime crisis, between June-2007 until June 2009, as shown in Grassi and Santucci de Magistris (2015). Instead, in the period 2003-2007, the RV is not subject to major breaks and we expect the parameters to be rather stable through time.…”

Section: Empirical Applicationmentioning

confidence: 99%

“…We estimate the parameters of the two‐factor Heston model (TFSV henceforth) on the RV series of JP Morgan (JPM) from July 2, 2003 to June 29, 2007 using intradaily returns sampled at a 5‐second frequency; that is, n = 4,680. The choice of sample period is motivated by the evidence of parameter instability for the TFSV model during the subprime crisis, between June 2007 and June 2009, as shown in Grassi and Santucci de Magistris (). The RV series is computed with returns sampled at two frequencies: 5 seconds and 5 minutes, RV 5s and RV 5m respectively.…”

Section: Empirical Applicationmentioning

confidence: 99%

Indirect inference with time series observed with error

Rossi

Magistris

2018

J of Applied Econometrics

View full text Add to dashboard Cite

We analyze the properties of the indirect inference estimator when the observed series are contaminated by measurement error. We show that the indirect inference estimates are asymptotically biased when the nuisance parameters of the measurement error distribution are neglected in the indirect estimation. We propose to solve this inconsistency by jointly estimating the nuisance and the structural parameters. The range of applicability of this methodology is supported by theoretical results based on several examples for both discrete and continuous-time models. Indirect inference is used to estimate the parameters of stochastic volatility models with auxiliary specifications based on realized volatility measures. Monte Carlo simulations show the bias reduction of the indirect estimates obtained when the microstructure noise is explicitly modeled. Finally, an empirical application illustrates the relevance of a realistic specification of the microstructure noise distribution to match the features of the observed log-returns at high frequencies.

show abstract

It's all about volatility of volatility: Evidence from a two-factor stochastic volatility model

Cited by 15 publications

References 69 publications

Forecasting the price of gold using dynamic model averaging

Forecasting the price of gold using dynamic model averaging

Forecasts for leverage heterogeneous autoregressive models with jumps and other covariates

Indirect inference with time series observed with error

Contact Info

Product

Resources

About