论文信息 - The Information Efficiency of Econometric Model Forecasts

The Information Efficiency of Econometric Model Forecasts

The informational efficiency of econometric model forecasts made by Data Resources, Incorporated and Chase Econometrics is evaluated. The criterion tested is an implication of the rational expectations hypothesis. Statistically significant serial correlations are found for several series of one-period forecast revisions, indicating rejection of the efficiency hypothesis. The use of these one-period revisions avoids some problems that have plagued previous tests that employed different efficiency criteria. Alternative explanations of the empirical results are suggested and analyzed.

Allen N. Berger | Spencer D. Krane

[1] Charles R. Nelson,et al. The Ex Ante Prediction Performance of the St. Louis and FRB-MIT-PENN Econometric Models and Some Results on Composite Predictors , 1975 .

[2] Neil Wallace,et al. Tests for Structural Change and Prediction Intervals for the reduced Forms of Two Structural Models of the U.S.: The FRB-MIT and Michigan Quarterly Models , 1974 .