Re-estimation of Keynesian Model by Considering Critical Events and Multiple Cointegrating Vectors

This study employs the Mundell (1963) and Fleming (1962)traditional flow model of exchange rate to examine the long runbehaviour of rupee/US $ exchange rate for Pakistan economy over theperiod 1982:Q1 to 2010:Q2. This study investigates the effect of outputlevels, interest rates and prices and different shocks on exchange rate.Hylleberg, Engle, Granger, and Yoo (HEGY) (1990) unit root test confirmsthe presence of non-seasonal unit root and finds no evidence of biannualand annual frequency unit root in the level of series. Johansen andJuselious (1988, 1992) likelihood ratio test indicates three long-runcointegrating vectors. Cointegrating vectors are uniquely identified byimposing structural economic restrictions on purchasing power parity(PPP), uncovered interest parity (UIP) and current account balance.Finally, the short-run dynamic error correction model is estimated onthe basis of identified cointegrated vectors. The speed of adjustmentcoefficient indicates that 17 percent of divergence from long-runequilibrium exchange rate path is being corrected in each quarter. USwar with Afghanistan has significant impact on rupee in short runbecause of high inflows of US aid to Pakistan after 9/11. Finally, theparsimonious short run dynamic error correction model is able to beatthe naïve random walk model at out of sample forecasting horizons. JELClassification: F31, F37, F47 Keywords: Exchange Rate Determination,Keynesian Model, Cointegration, Out of Sample Forecasting, Random WalkModel