Energy consumption, employment, output, and temporal causality: evidence from Taiwan based on cointegration and error-correction modelling techniques

Abstract

In this study, a cointegration analysis and a vector autoregressive model (VAR) are used to examine the causal relationships among energy consumption, employment, and output for Taiwan over the period January 1982 to November 1997. Johansen (1988) and Johansen and Juselius (1990) cointegration test result indicates these three variables are cointegrated with one cointegrating vector. The results from Granger causality tests based on vector error-correction models (VECM) suggest bidirectional Grange causality for employment-output and employment-energy consumption, but only unidirectional causality running from energy consumption to output. Furthermore, the impulse responses and variance decompositions are also incorporated into the analysis. The results from impulsive response and variance decomposition analysis tell similar stories. Energy consumption appears to have led to output growth in Taiwan over this period. The policy implication of this finding is that energy conservation will restrain the output growth in Taiwan.