Do U.S. economic conditions at the state level predict the realized volatility of oil-price returns? A quantile machine-learning approach

Rangan Gupta; Christian Pierdzioch

doi:10.1186/s40854-022-00435-5

Do U.S. economic conditions at the state level predict the realized volatility of oil-price returns? A quantile machine-learning approach

Financ Innov. 2023;9(1):24. doi: 10.1186/s40854-022-00435-5. Epub 2023 Jan 12.

Authors

Rangan Gupta¹, Christian Pierdzioch²

Affiliations

¹ Department of Economics, University of Pretoria, Pretoria, 0002 South Africa.
² Department of Economics, Helmut Schmidt University, Holstenhofweg 85, P.O.B. 700822, 22008 Hamburg, Germany.

Abstract

Because the U.S. is a major player in the international oil market, it is interesting to study whether aggregate and state-level economic conditions can predict the subsequent realized volatility of oil price returns. To address this research question, we frame our analysis in terms of variants of the popular heterogeneous autoregressive realized volatility (HAR-RV) model. To estimate the models, we use quantile-regression and quantile machine learning (Lasso) estimators. Our estimation results highlights the differential effects of economic conditions on the quantiles of the conditional distribution of realized volatility. Using weekly data for the period April 1987 to December 2021, we document evidence of predictability at a biweekly and monthly horizon.

Keywords: Economic conditions indexes; Oil price; Prediction models; Quantile Lasso; Realized volatility.