Oil price and industrial production in G7 countries: Evidence from the asymmetric and non-asymmetric causality tests

After the oil shock of 1973, studies on causal nexus between oil price and economic growth have increasingly appeared in the literature. Unlike extant literature, this study deals with two problems related to causality estimation. The first one is which oil price should be used in empirical analyses as the price of oil differs among different oil products. Instead of crude oil price, oil basket price calculated by OPEC was used in this paper since it does not exclude the price of other oil types. Second problem is that positive and negative shocks in the independent variables may asymmetrically affect dependent variable. Distinguishing positive and negative shocks may lead to different findings. Moreover asymmetric causality test may lead to inference about the sign of the causal nexus. In this study asymmetric causal links were taken into account using the novel asymmetric causality approach developed by Hatemi-J (2012). Furthermore non-normality of the error term and time varying volatility may lead to biased estimation results. So a bootstrap simulation approach developed by Hacker and Hatemi-J (2006) was used to generate critical values that are robust to non-normality and time-varying volatility. In addition, classical non-asymmetric causality test was applied with the aim of comparison. The monthly data set covers the period of 2003:1-2013:1. (C) 2014 Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/3.0/).