Stock and oil price returns in international markets: Identifying short and long-run effects

Abstract

This paper examines how stock returns respond to oil prices with monthly data from 1990 to 2020 for 12 major economies: 6 oil-exporting countries and 6 oil-importing countries. Combining short and long-run empirical approaches in country-by-country analyses, we first document varying effects of oil price returns in the short-term, while increases in volatility (changes in VIX or geopolitical risk) have negative effects on stock markets. Dynamic OLS (DOLS) estimators show in the long-run positive oil price effects on stock markets for oil-exporters and relatively weaker negative evidence for oil-importers. Interest rate increases have strong negative effects in the long run. Panel analyses shed further light on these results along with structural breaks. Our findings suggest complementary insights from the DOLS long-run approach: oil prices and bond yields have expected signs and volatility has mixed effects on stock markets. Supplementary Information The online version contains supplementary material available at 10.1007/s12197-022-09602-x.

Dynamic spillover between crude oil, gold, and Chinese stock market sectors –analysis of spillovers during financial crisis data during the last two decades

“…Some studies observe an amplification of spillover effects following the 2008 global financial crisis, underscoring the necessity for dynamic analysis [ 21 ]. While gold may potentially act as a hedge against oil price volatility, its effectiveness appears limited in the Chinese context [ 22 ]. Research suggests that the hedging power of gold varies across sectors and economic conditions [ 23 ].…”

The Impact of Investor Attention on China’s Corn Futures Price

“…Traditional statistical methods provide great prediction results under the linear assumption. For example, linear regression model [1], autoregressive integrated moving average model (ARIMA) [2], autoregressive conditional heteroskedasticity (ARCH) [3], generalized autoregressive conditional heteroskedasticity (GARCH) [4], and vector autoregressive regression (VAR) [5]. Because the financial time series is complicated, dynamic, and non-linear, various approaches which belong to the machine learning field have been employed to build the prediction model.…”