Terrorism in Nigeria: A Dynamic Time Series Framework

Abstract

This study examines the effect of economic, social, political, demographic, geographic and environmental factors on domestic terrorism in Nigeria between1970 and 2012. Estimates, based on the boundstesting procedure to cointegration within an autoregressive distributed lag(ARDL) framework and error correction specification, indicate that LOG(HDI), LOG(GINI), POLS, TERR(-1), DLOG(POPG), DLOG(OEXP(-1)) and DLOG(OEXP) have a positive impact on terrorism in the short run. On the other hand, LOG(GOVX), LOG(POPG), DLOG(GINI(-1)) and LOG(INFL) have a negative relationship with terrorism. The long run static relationship shows that LOG(HDI), POLS and LOG(UBAN) positive impact on terrorism while LOG(INFL), LOG(GDPC) and LOG(GOVX) exhibit inverse relationship with terrorism. The results further show that, the error correction mechanism (ECM) indicates that a deviation from the long-run equilibrium following a short-run shock is corrected by about 41 per cent after each year.

Key words:Terrorism, Autoregressive Distributed Lag Model.