Global equity market volatility forecasting: New evidence

Abstract

Abstract In this paper, we extend the work of Buncic and Gisler,International Journal of Forecasting, 2016,32, 1317–1339 and investigate that whether US‐based stock volatility information and crude oil volatility information have predictability for forecasting the realized volatility (RV) of global equity markets from both in‐ and out‐of‐sample perspectives in a changing world. The HAR‐RV model is our benchmark model. We utilize two popular shrinkage methods of the elastic net and lasso to solve the overfitting problem. In addition, we establish the HAR‐RV‐AVERAGE model by an easy combination approach. Our empirical results indicate that the HAR‐RV‐AVERAGE model exhibits the best prediction performance in predicting the RV of most indices and developed countries equity markets benefit the most from the inclusion of US‐based crude oil and equity market volatility information, while emerging country stock markets benefit the least, especially for Asian equity indices. Alternative out‐of‐sample periods and alternative volatility estimator confirm the robustness of our results.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 39 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.