论文信息 - The Optimal Use of Provisional Data in Forecasting With Dynamic Models

The Optimal Use of Provisional Data in Forecasting With Dynamic Models

Timely economic forecasts by means of dynamic models rely on updated time series, the last figure(s) of which are provisional and will be typically subjected to a number of revisions. A general approach to the efficient use of provisional observations in dynamic models is presented, based on the state-space methodology and the Kalman filter. Suitable adaptations are introduced, chiefly involving the measurement equations. Some applications are carried out for Italy, concerning (a) the monthly index of industrial production and (b) a small dynamic simultaneous-equation model of the aggregate economy. Kalman-filter estimates and predictions are compared with more traditional procedures.

Silvano Bordignon | Ugo Trivellato | U. Trivellato | S. Bordignon

[1] P. Schmidt,et al. Estimation of Seemingly Unrelated Regressions with Vector Autoregressive Errors , 1973 .

[2] E. Philip Howrey,et al. Data Revision, Reconstruction, and Prediction: An Application to Inventory Investment , 1984 .

[3] C. Granger. Investigating Causal Relations by Econometric Models and Cross-Spectral Methods , 1969 .

[4] G. Chow. Analysis and control of dynamic economic systems , 1975 .

[5] D. A. Pierce. Sources of error in economic time series , 1981 .

[6] Enrico Rettore,et al. Preliminary Data Errors and Their Impact on the Forecast Error of Simultaneous-Equations Models , 1986 .

[7] Carol Corrado,et al. Application of the Kalman filter to revisions in monthly retail sales estimates , 1979 .

[8] E. P. Howrey,et al. The Use of Preliminary Data in Econometric Forecasting , 1978 .

[9] A. Zellner. An Efficient Method of Estimating Seemingly Unrelated Regressions and Tests for Aggregation Bias , 1962 .

[10] R. Engle,et al. Alternative Algorithms for the Estimation of Dynamic Factor , 1983 .

[11] A. Harvey. Time series models , 1983 .