Forecast Uncertainties in Macroeconometric Modelling: An Application to the UK Economy

By Anthony Garratt, Kevin Lee, M. Hashem, Pesaran, Yongcheol Shin, Manuel Arellano, Michael Binder, David Hendry, Ron P. Smith, K. Wallis. Social Science Research Network, 2000

133 citations recorded by the source corpus.

This paper argues that probability forecasts convey information on the uncertainties that surround macro-economic forecast in straightforward manner which is preferable to other alternatives, including the use of confidence intervals. Point and probability forecasts obtained using a small macro-economic model are presented and evaluated using recursive forecasts generated from the model over the period 1999-2000. Out of sample probability forecasts of inflation and output growth are also provided over the period 2001-2003, and their implications discussed in relation to the Bank of England's inflation target and the need to avoid recessions, both as separate events and jointly. It is also shown how the probability forecasts can be used to provide insights on the inter-relationship of output growth and inflation at different horizons.

Subfields: Economics and Econometrics

View Paper: https://www.semanticscholar.org/paper/b475f7427dc6419231521451fe7a57ee4eb15b64

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Economics and Econometrics

Citations in the corpus

Model Averaging and Its Use in Economics (2017, methodology): “George and Foster (2000) develop a global EB approach, which assumes one common g and w for all models and borrows strength from all models by estimating g and w through maximizing the marginal likelihood, averaged over all models.”
What if the UK or Sweden had joined the Euro in 1999? An empirical evaluation using a global VAR (2007, methodology): “In the case of the entry restrictions (7) and (8) we have l = 2,”
Forecasting with Factor-Augmented Regression: A Frequentist Model Averaging Approach, Second Version (2013, methodology): “In consequence, these frequentist model averaging criteria can be applied to factor-augmented forecast combination without modification.”
Model Averaging and Value-at-Risk Based Evaluation of Large Multi Asset Volatility Models for Risk Management (2004, unknown): “Recent applications to time series econometrics are provided in Fernandez et al. (2001a,b), Garratt, Lee, Pesaran, and Shin (2003) and Godsill, Stone, and Weeks (2004).”
Testing Forecast Optimality Under Unknown Loss (2007, unknown): “During periods of high economic growth, the loss function is approximately symmetric, whereas when realized GDP growth is at a lower level, the asymmetry becomes more pronounced, and, as in the simpler model, overpredictions are penalized more heavily than underpredictions.”
Least-squares forecast averaging (2008, background): “Some applications in econometrics include Sala-i-Martin et al. (2004), Brock and Durlauf (2001), Avramov (2002), Fernandez et al. (2001a,b), Garratt et al. (2003) and Brock et al. (2003).”
Probabilistic forecasts, calibration and sharpness (2007, methodology): “Formal tests of uniformity can be employed and have been studied by Anderson (1996), Talagrand et al. (1997), Noceti et al. (2003), Garratt et al. (2003), Wallis (2003), Candille and Talagrand (2005) and Corradi and Swanson (2006), among others.”
Strictly Proper Scoring Rules, Prediction, and Estimation (2007, background): “In prediction problems, proper scoring rules encourage the forecaster to make careful assessments and to be honest.”
Evaluating, Comparing and Combining Density Forecasts Using the KLIC with an Application to the Bank of England and NIESR 'Fan' Charts of Inflation (2005, unknown): “5 Garratt et al. (2003) and Pesaran & Zaffaroni (2004) have also considered the combination of probability forecasts using BMA.”
Likelihood-based scoring rules for comparing density forecasts in tails (2011, background): “Undoubtedly, this is due to the increased awareness that point forecasts are not very informative unless some indication of their uncertainty is provided; see Granger and Pesaran (2000) and Garratt et al.”
Path Forecast Evaluation (2010, methodology): “Similarly, the assumption of Gaussian errors could be relaxed, but then the distribution of the forecast errors would no longer be Normal and should be obtained by means of simulation methods, see e.g. Garratt et al. (2003).”