Forecasting Volatility in Digital Assets: A Comparative Study

Modeling the volatility of cryptocurrencies is important for understanding and managing risk in these markets. Reference [1] provides a literature review of various volatility prediction approaches and evaluates three models: GARCH, EGARCH, and EWMA.

The EGARCH model is an extension of the GARCH model that accounts for the asymmetric impact of positive and negative shocks on volatility. It reflects the common belief that bad news tends to cause larger market reactions than equally sized good news. The authors pointed out,

The EGARCH (1,1) volatility estimation model demonstrated superior performance. This finding aligns with the outcomes of a study conducted by Alexander and Dakos (2023), Ngunyi et al. (2019), and Naimy and Hayek (2018) demonstrating that the asymmetric GARCH model exhibited superior performance across several cryptocurrencies. Further, Bergsli et al. (2022) found that the EGARCH and APARCH model exhibited superior performance compared to other GARCH models. According to the findings of the aforementioned study, the GARCH (1,1), EGARCH (1,1), and EWMA volatility estimation model exhibited limitations in capturing high volatility fluctuations and demonstrate improved accuracy when the observed daily volatility is at a lower level. However, it is crucial to acknowledge that the aforementioned discoveries are only relevant to Bitcoin and Ethereum. The maximum threshold of high volatility is expected to be linked to the degree of uncertainty. This finding might assist investors and prospective investors in evaluating the risks and rewards associated with the Bitcoin and Ethereum.

In short, the EGARCH(1,1) model performs the best for both Bitcoin and Ethereum.

This article is important because it highlights effective tools for forecasting crypto market volatility. It also discusses the weaknesses of these forecast models, notably their limitations in capturing periods of high volatility, while showing improved accuracy when daily volatility is relatively low.

Let us know what you think in the comments below or in the discussion forum.

References

[1] Irawan, Andree and Utam, Wiwik, Modelling cryptocurrency price volatility through the GARCH and EWMA model, Management & Accounting Review (MAR), 24 (1): 6. pp. 153-179.

Article Source Here: Forecasting Volatility in Digital Assets: A Comparative Study

source https://harbourfronts.com/forecasting-volatility-digital-assets-comparative-study/