Search

Any research or policy analysis in economics must be consistent with the time-series properties of observed macroeconomic data. Numerous previous studies reinforce the need to specify correctly a model's multivariate stochastic structure. This paper discusses in detail the specification of a vector error correction forecasting model that is anchored by long-run equilibrium relationships suggested by economic theory. The model includes six variables--the CPI, the GDP price index, real money balances (M1), the federal funds rate, the yield on long-term (10-year) government bonds, and real GDP--and four cointegrating vectors. The accuracy of VECM model forecasts for individual, univariate time series during for the 1990s is comparable to forecasts made by government agencies and private forecasters, perhaps because many forecasters share a similar implicit, long-run steady-state growth model of the economy. Judged by multivariate statistics that account for forecast-error covariance, VECM forecasts are found to be somewhat more accurate than a naive random-walk alternative. JEL classification: C32; C53 Keywords: Forecasting; Cointegration; Vector error-correction models

The most significant effects of external shocks on the domestic economy materialize through the real exchange rates, leading to fluctuations even in large countries. On the one hand, lasting shocks in real exchange rates have influenced the flow of business cycles for the last thirty years. As predetermined by macroeconomic models of open economies, the impact of shocks in the exchange rates is manifested through the net exports. On the other hand, modifications in foreign output, while influential in determining net exports, do not have significant effects on local real variables.

The constancy of long-term demand for money in the US, Japan, Canada, West Germany and the UK was studied by analyzing quarterly data on money supply from various sources and data bases dating from 1955. The estimation methodologies used were Johansen's p-dimension vector autoregression approach and Watson's cointegrating relations. For all countries studied, a significant correlation between nominal interest rates and money velocity was discovered.