FORECASTING VOLATILITY WITH HAR-RV: INSIGHTS FROM COMMODITIES, CURRENCIES, AND EQUITIES

Atak A.

Anadolu Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi, cilt.26, sa.4, ss.570-585, 2025 (TRDizin)

Özet

This article analyzes the volatility dynamics of a mixed set of assets comprising a global commodity (gold), a currency pair (USD/TRY), and a domestic equity index (Borsa Istanbul) using high-frequency data. We apply the Heterogeneous Autoregressive Realized Volatility (HAR-RV) model to capture persistence and cross-horizon effects across daily, weekly, and monthly intervals. The model outperforms short-memory alternatives in both in-sample and out-of-sample forecasts, with robust results confirmed by MSE, QLIKE, and Diebold-Mariano tests. Weighted Least Squares estimation enhances efficiency in the presence of heteroscedasticity. The findings highlight HAR-RV’s strength in modeling multiscale volatility, offering practical value for risk management and policy-making, especially in emerging markets.