The Role of Jumps and Leverage in Forecasting Volatility in International Equity Markets

Bunčić, Daniel; Gisler, Katja I. M.

doi:10.2139/ssrn.2835570

Cited by 14 publications

(24 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A reasonable explanation as to why the TVTP-MRS-MIDAS-LCJ model is the best forecasting model lies in the fact that the Bitcoin market has high fluctuations and the TVTP model allows the transition probabilities between different jump-volatility regimes to change according to economic or market conditions; the leverage effect can increase the accuracy of the forecast, and various studies also support this (see, e.g., Buncic & Gisler, 2017;Choi & Richardson, 2016;Corsi & Renò, 2012).…”

Section: Out-of-sample Resultsmentioning

confidence: 99%

Cryptocurrency volatility forecasting: A Markov regime‐switching MIDAS approach

Liang

et al. 2020

Journal of Forecasting

View full text Add to dashboard Cite

The primary purpose of this paper is to investigate whether a novel Markov regime-switching mixed-data sampling (MRS-MIADS) model we design can improve the prediction accuracy of the realized variance (RV) of Bitcoin. Moreover, to verify whether the importance of jumps for RV forecasting changes over time, we extend the standard MIDAS model to characterize two volatility regimes and introduce a jump-driven time-varying transition probability between the two regimes. Our results suggest that the proposed novel MRS-MIDAS model exhibits statistically significant improvement for forecasting the RV of Bitcoin. In addition, we find that jump occurrences significantly increase the persistence of the high-volatility regime and switch between high-and low-volatility regimes. A wide range of checks confirm the robustness of our results. Finally, the proposed model shows significant improvement for 2-week and 1-month horizon forecasts.

show abstract

Section: Out-of-sample Resultsmentioning

confidence: 99%

Cryptocurrency volatility forecasting: A Markov regime‐switching MIDAS approach

Liang

et al. 2020

Journal of Forecasting

View full text Add to dashboard Cite

show abstract

“…Although it can successfully forecast stock market volatility, the HAR benchmark model may ignore some important factors. In this section, we follow Buncic and Gisler (2017), who emphasize the importance of jumps and leverage effects to forecasts of international stock market volatility, and extend the benchmark model by considering jumps and leverage effects separately. Due to the availability of jump data, we use the most simple jump measure proposed in the influential work of Andersen et al (2007).…”

Section: Jump and Leveragementioning

confidence: 99%

“…Finally, following Buncic and Gisler (2017), who emphasize the importance of jumps and the leverage effect to forecasting international stock market volatilities, we use the HAR-RV-J model proposed by Andersen et al (2007) and the HAR-RV-L model proposed by Corsi and Renò (2012) as additional benchmark models to determine whether information flows with IV are still more effective than information flows with RV in predicting international stock market volatility. The corresponding out-of-sample results are consistent with the results based on the HAR-RV benchmark model.…”

Section: Introductionmentioning

confidence: 99%

“…Therefore, we can conclude that the out-of-sample Notes: This table reports one-step-ahead out-of-sample forecast evaluation results by the DM test for the models with information flow of realized volatility relative to the competing models, which totally includes eight sets of models for each considered stock market. In this table, we employ another prevailing benchmark of HAR-RV-J model due to the importance of leverage effect according to Buncic and Gisler (2017). The specification of the HAR-RV-J model can be expressed as (23).…”

mentioning

confidence: 99%

See 1 more Smart Citation

Is implied volatility more informative for forecasting realized volatility: An international perspective

Liang

Wei

Zhang

2020

Journal of Forecasting

View full text Add to dashboard Cite

Inspired by the commonly held view that international stock market volatility is equivalent to cross-market information flow, we propose various ways of constructing two types of information flow, based on realized volatility (RV) and implied volatility (IV), in multiple international markets. We focus on the RVs derived from the intraday prices of eight international stock markets and use a heterogeneous autoregressive framework to forecast the future volatility of each market for 1 day to 22 days ahead. Our Diebold-Mariano tests provide strong evidence that information flow with IV enhances the accuracy of forecasting international RVs over all of the prediction horizons. The results of a model confidence set test show that a market's own IV and the first principal component of the international IVs exhibit the strongest predictive ability. In addition, the use of information flows with IV can further increase economic returns. Our results are supported by the findings of a wide range of robustness checks.

show abstract

“…More specifically, Aganin (2017) compare the GARCH, ARFIMA and HAR-RV models and the results show that HAR-RV model has superior performance than GARCH and ARFIMA models; moreover, Vortelinos (2017) compares the forecasting performance of nonlinear models (Principal Components Combining, neural networks and GARCH) and HAR-RV model, the result indicate the simple HAR model is the most accurate for seven US financial markets (spot equity, spot foreign exchange rates, exchange traded funds, equity index futures, US Treasury bonds futures, energy futures, and commodities options). Furthermore, Buncic and Gisler (2017) employ the HAR-RV-type models to investigate the role of jump and leverage effect in forecasting international stock market volatility; moreover, from global international market perspective, Zhang, Ma, and Liao (2020) focus on cross-national volatility flows and also employ the HAR-RV-type models. Given the success of the HAR-RV-type models, we follow abovementioned studies and set HAR-RV model as our benchmark.…”

Section: Introductionmentioning

confidence: 99%