Linear constraints and the efficiency of combined forecasts

Studies of combined forecasts have typically constrained the combining weights to sum to one and have not included a constant term in the combination. In a recent paper, Granger and Ramanathan (1984) have argued in favour of an unrestricted linear combination, including a constant term. This paper s...

Full description

Saved in:
Bibliographic Details
Published inJournal of forecasting Vol. 5; no. 1; pp. 31 - 38
Main Author Clemen, Robert T.
Format Journal Article
LanguageEnglish
Published Chichester John Wiley & Sons, Ltd 01.01.1986
Wiley
Wiley Periodicals Inc
Subjects
Bias
Combined
Combining forecasts
Efficiency
Forecast efficiency
Forecasting techniques
Forecasts
GNP
Gross National Product
Linear constraints
Mathematical models
Regression
Statistical methods
Online AccessGet full text

Cover

More Information
Summary:Studies of combined forecasts have typically constrained the combining weights to sum to one and have not included a constant term in the combination. In a recent paper, Granger and Ramanathan (1984) have argued in favour of an unrestricted linear combination, including a constant term. This paper shows that for the purpose of prediction it may make sense to impose restrictions on the combining model because of potential increases in forecasting efficiency. Empirical results show that small gains in forecasting efficiency can be obtained by restricting the linear combination of GNP forecasts from four econometric models.
Bibliography:ark:/67375/WNG-JFZQKD6F-0
istex:F04F6B33F1A8E8446DAC8D5C05E3D7CFB94BDFF9
ArticleID:FOR3980050104
Operations Research, Management Science, Journal of Business Economics and Statistics
Journal of Forecasting.
Robert T. Clemen is an Assistant Professor of Business at the University of Oregon. He has a Ph.D. in Quantitative Business Analysis from Indiana University. His research interests are in combining forecasts, decision theory and Bayesian statistics, and he has published articles in
and
ISSN:0277-6693
1099-131X
DOI:10.1002/for.3980050104