Predicting the Volatility of Cryptocurrencies’ Returns Using High-Frequency Data: A Comparative Analysis of GARCH, EGARCH, IGARCH, GJR-GARCH, LRE, and HAR Models
Open Access
- 3 April 2026
- journal article
- research article
- Published by MDPI AG in International Journal of Financial Studies
- Vol. 14 (4) , 90
Abstract
This study provides a comprehensive evaluation of six volatility forecasting models applied to twelve dominant and less dominant cryptocurrencies across multiple time horizons using high-frequency intraday data. The exponential generalized autoregressive conditional heteroskedastic (EGARCH), integrated GARCH (IGARCH), standard GARCH, GJR-GARCH, lagged realized volatility (LRE), and heterogeneous autoregressive (HAR) models are systematically compared using 5 min computed return data from September 2018 to September 2020. Our analysis encompasses three forecast horizons (1-day, 7-day, and 30-day) to assess model performance under varying temporal constraints. Through univariate Mincer–Zarnowitz regressions, encompassing tests, and out-of-sample evaluation using root mean squared error (RMSE) and quasi-likelihood loss (QLIKE) functions, we identify significant performance heterogeneity across models and cryptocurrencies. The HAR model exhibits stronger predictive accuracy at short horizons, while EGARCH exhibits relatively stronger performance at longer horizons, although overall explanatory power declines as forecast horizon increases. Importantly, no single model consistently provides optimal forecasts across all cryptocurrencies. Consistent with prior evidence suggesting model performance varies across assets. Encompassing regressions reveal that combining HAR with EGARCH specifications significantly enhances explanatory power across all temporal frames. Out-of-sample Diebold–Mariano tests indicate that HAR generates the lowest forecast errors for most cryptocurrencies, though EGARCH performs exceptionally well for high-market-capitalization assets. These findings provide regime-conditional insights into horizon- and asset-specific volatility dynamics during the pre-institutionalization phase of cryptocurrency markets. The study contributes to emerging literature by incorporating less-dominant cryptocurrencies and offering robust empirical evidence on the asymmetric and persistent volatility characteristics unique to digital asset markets. These findings should be interpreted within the context of the 2018–2020 sample period, representing a pre-institutionalized phase of cryptocurrency markets, and may not fully generalize to structurally different market regimes characterized by increased institutional participation and regulatory development.Keywords
Funding Information
- Imam Mohammad Ibn Saud Islamic University (IMSIU-DDRSP2604)
This publication has 43 references indexed in Scilit:
- Regime switching and causal network analysis of cryptocurrency volatility: evidence from pre-COVID and post-COVID analysisDigital Finance, 2024
- Forecasting realized volatility of Bitcoin: The informative role of price durationJournal of Forecasting, 2023
- Portfolio management with cryptocurrencies: The role of estimation riskEconomics Letters, 2019
- Asymmetric volatility in cryptocurrenciesEconomics Letters, 2018
- VIX term structure and VIX futures pricing with realized volatilityJournal of Futures Markets, 2018
- Volatility estimation for Bitcoin: A comparison of GARCH modelsEconomics Letters, 2017
- An International Comparison of Implied, Realized, and GARCH Volatility ForecastsJournal of Futures Markets, 2016
- Speculative bubbles in Bitcoin markets? An empirical investigation into the fundamental value of BitcoinEconomics Letters, 2015
- A forecast comparison of volatility models: does anything beat a GARCH(1,1)?Journal of Applied Econometrics, 2005
- Generalized autoregressive conditional heteroskedasticityJournal of Econometrics, 1986