Forecasting the dynamic relationship between crude oil and stock prices since the 19th century

Kris Ivanovski, Abebe Hailemariam

Research output: Contribution to journalReview ArticleResearchpeer-review

Abstract

In this paper, we model and forecast the volatility and correlation between oil prices and stock returns. Employing a recently innovated generalized autoregressive score (GAS) model based on the score function and using long historical data spanning from 1871 to 2020, we find a time-varying relationship between oil prices and stock returns. Specifically, the dynamic correlations between crude oil and stock returns tend to rise during turbulent events over the sample period significantly. Our results show that the GAS(1,1) model outperforms the DCC-GARCH model. Our results on the dependent patterns between oil price and stock returns provide useful information for investors, portfolio managers and market participants.

Original languageEnglish
Article number100169
Number of pages12
JournalJournal of Commodity Markets
DOIs
Publication statusAccepted/In press - 2021

Keywords

  • DCC-GARCH model
  • Forecasting
  • Multivariate GAS model
  • Oil price
  • Stock price
  • Volatility and correlation

Cite this