Staff Working Paper No. 1,078
Derrick Kanngiesser and Tim Willems
We propose a systematic approach for central banks to leverage past forecasts (and associated errors) with the aim of learning more about the structure and functioning of the underlying economy. Applying this method to forecasts made by the Bank of England’s Monetary Policy Committee since 2011, we find that its forecasts have tended to underestimate pass‑through from wage growth, whilst also featuring a Phillips curve that is too flat. Regarding the effects of monetary policy, our results point to transmission via inflation expectations possibly having played a bigger role than attributed to it in the forecast. We also provide a more classical evaluation of forecast errors – finding inflation forecasts to have been unbiased. At the same time, however, inflation forecasts tend to be less accurate than those for real GDP growth, unemployment, and wage growth. This seems attributable to greater inherent uncertainties in the inflation process.
Forecast accuracy and efficiency at the Bank of England – and how errors can be leveraged to do better