Assistant Professor of Economics in the Babcock Graduate School of Management, Wake Forest University. He was the Chemicals Division Economist for Phillips Petroleum Company, 1980-86, and Associate Consultant for Data Resources, Inc., 1978-79. His education includes a Ph.D. in Economics from Southern Methodist University, 1986, a M.S. in Economics from Iowa State University, 1978 and a B.S. in Mathematics and Economics from Kansas State College, Pittsburg, 1976. His main research interests include regional forecasting, time series forecasting, business cycles, econometrics and industrial organization. He has authored papers in Applied Economics, International Regional Science Review and Review of Industrial Organization.
Co-integration, error correction and improved medium-term regional VAR forecasting
Version of Record online: 2 NOV 2006
Copyright © 1992 John Wiley & Sons, Ltd.
Journal of Forecasting
Volume 11, Issue 2, pages 91–109, February 1992
How to Cite
Shoesmith, G. L. (1992), Co-integration, error correction and improved medium-term regional VAR forecasting. J. Forecast., 11: 91–109. doi: 10.1002/for.3980110202
- Issue online: 2 NOV 2006
- Version of Record online: 2 NOV 2006
- Manuscript Revised: AUG 1990
- Manuscript Received: OCT 1989
- Error correction;
- Regional forecasting;
- Vector autoregression;
- Bayesian vector autoregression
This study investigates possible improvements in medium-term VAR forecasting of state retail sales and personal income when the two series are co-integrated and represent an error-correction system. For each of North Carolina and New York, three regional vector autoregression (VAR) models are specified; an unrestricted two-equation model consisting of the two state variables, a five-equation unrestricted model with three national variables added and a Bayesian (BVAR) version of the second model. For each state, the co-integration and error-correction relationship of the two state variables is verified and an error-correction version of each model specified. Twelve successive ex ante five-year forecasts are then generated for each of the state models. The results show that including an error-correction mechanism when statistically significant improves medium-term forecasting accuracy in every case.