Testing Okun’s law at sectoral level: evidence from Nigeria

Abstract

Purpose Researchers have long been interested in testing the validity of Okun’s law due to its macroeconomic policy implications. However, most of the studies have focused on testing the law using aggregate data on unemployment and output. In recent times, attention has been shifted to testing the law at the sectoral level. In light of this, the purpose of this study is to examine the response of unemployment to sectoral outputs in Nigeria using the data that covers a period from 1981-2020. Design/methodology/approach To test the validity of Okun’s law at the sectoral level, both difference and gap methods of specifying Okun’s law are used. Furthermore, the author also uses a series of estimation methods, which include ordinary least squares (OLS), dynamic OLS (DOLS), fully modified OLS (FMOLS) and canonical cointegration regression (CCR). Findings The results, based on the difference model, are mixed irrespective of estimation and data filter methods. For the gap model, Okun’s law holds for all sectors irrespective of estimation techniques (especially DOLS, FMOLS and CCR) when the Hodrick–Prescott filter method is used to filter data. However, the author discovers that the coefficients of Okun’s law vary across the sectors as the response of unemployment to services sector output is greater than the rest of the sectors. When the Hamilton filter method is used to filter data, the results appear to be mixed across the sectors. The results are almost ditto when all the sectoral variables are put in one model. Originality/value To the best of the author’s knowledge, this is the first study that investigates the validity of sectoral Okun’s law in Nigeria, the leading economy in Africa.