Article ID: | iaor2009385 |
Country: | Germany |
Volume: | 6 |
Issue: | 3/4 |
Start Page Number: | 183 |
End Page Number: | 191 |
Publication Date: | Jul 1998 |
Journal: | Central European Journal of Operations Research |
Authors: | Hatrk Michal |
Keywords: | time series & forecasting methods |
Until not many years ago economists analyzed time series data with the help of econometrtc methodology that was quite different from the statistician's time series methodology (Box–Jenkins approach). Econometric approach to analysis of economic data was based on traditional regression model that was used as a representation of the behavior of economic variables measured by time series data. The generalization of this approach had the form of simultaneous equation model. This methodology paid big attention to such problems as autocorrelation of random disturbances, multicollinearity, simultaneity, and so on. Very little attention was paid to the specification of the dynamic structure of the model.