Bayesian inference requires an analyst to set priors. Setting the right prior is crucial for precise forecasts. This paper analyzes how optimal prior changes when an economy is hit by a recession. For this task, an autoregressive distributed lag model is chosen. The results show that a sharp...

Forecasts of inflation in the United States since the mid eighties have had smaller errors than in the past, but those conditional on commonly used variables cannot consistently beat the ones from univariate models. This paper shows through simple modifications to the classical monetary model...