Authors:
Jennifer L. Castle, Climate Econometrics and Calleva Project, Magdalen College
Jurgen A. Doornik, Climate Econometrics and Nuffield College
David F. Hendry, Climate Econometrics and Nuffield College
About the paper:
Distributional shifts occur frequently, with detrimental impacts on forecast accuracy. Almost all econometric forecasting models are equilibrium correction so are susceptible to systematic forecast failure after equilibrium-mean shifts, which could be direct or induced. Unanticipated out-of-sample shifts are a well-known cause of forecast failure, but they later become in-sample shifts so require handling. Previous forecast-error taxonomies are extended to include shifts both in-sample and after the forecast origin. The taxonomy reveals which shifts do and do not lead to forecast failure facing both in-sample and post forecast-origin shifts, also highlighting what features are amenable to rapid correction.
Full paper can be found here.
Data:
The data, PcGive batch files, and output can be downloaded from ESTaxonFiles.zip.
GDPt: Real Gross Domestic Product, Billions of Chained 2017 Dollars, SA: GDPC1
GDPt*: Real Potential Gross Domestic Product, Billions of Chained 2017 Dollars: FGDPPOT
Pt: Consumer Price Index for All Urban Consumers: All Items in U.S.: CPIAUCSL
City Average, Index 1982-1984=100, SA
Δ4Pt: (Pt-P(t-4))/P (t-4))x100
gapt: (GDPt-GDPt*)/GDPt*x100
All data are quarterly frequency and obtained from Federal Reserve Bank of St Louis: FRED. Real potential GDP is the CBO’s estimate of the output the economy would produce with a high rate of use of its capital and labor resources. The nominal GDP data is adjusted to remove the effects of inflation.”