A multivariate cointegrating vector auto regressive model of freight transport demand: evidence from Indian railways

In this paper long run structural relationship for freight transport demand is derived for railways in India using annual time series data for 1960-19 95. Some of the recent developments in multivariate dynamic econometric tim e series modelling have been employed such as estimation of long-run struct ural cointegrating relationship, short-run dynamics and measurement of the effects of shocks and their persistence during the evolution of dynamic fre ight transport demand system. The models are estimated using a cointegratin g vector autoregressive (VAR) modelling framework, which allows for endogen eity of regressors. Results indicate high GDP elasticity and low price elas ticity, with real freight rate, i.e. the price variable behaving exogenousl y with respect to I:he system. Any disequilibrium in the short-run is likel y to be corrected in the long run via adjustments in freight transport dema nd and GDP. Further, the demand system seems to be stable in the long run a nd converges to equilibrium in a period of around 3 years after a typical s ystem-wide shock. (C) 2000 Elsevier Science Ltd. All rights reserved.