IZA Discussion Paper No. 15666

The Determinants of Crude Oil Prices: Evidence from ARDL and Nonlinear ARDL Approaches

This paper is an innovative attempt to empirically investigate the determinants of crude oil prices. The main objective is to distinguish between short- and long-term effects of some covariates on oil prices. The autoregressive distributed lag (ARDL) approach is applied to daily series spanning the period from January 2, 2003, to May 24, 2021, to analyze long-run relationships and short-run dynamics. The paper also focuses on the asymmetric effects of covariates and a nonlinear ARDL (NARDL) approach is used to explore this asymmetry. The use of an asymmetric error correction model with asymmetric cointegration provides new insights for examining the determinants of oil prices. All investigations of underlying oil price fluctuations are examined both before and in the COVID-19 pandemic. Our results, based on different econometric specifications, have key policy implications for policymakers both with and without COVID-19 potential considerations.

All publications