Recent applications of the Vector Autoregression (VAR) technique pioneered by Sims, Litterman and Doan has become popular in macroeconomic modelling, particularly when knowledge about 'true' structural relations is absent. This study represents the first attempt to apply such a technique to Pakistani data for ten key macroeconomic variables. Unlike some of the earlier studies on Pakistan's economy our empirical results are intuitive and consistent with the predictions of the standard new neoclassical model. More importantly, based on these results, perhaps, one may also shed light on some of the dominant recurring macroeconomic issues of Pakistan's economy. © 1992.