Why forecasts don't work

John Kay of St John's College, Oxford explains why the scope for applying probabilistic type reasoning to economics is limited. Probabilistic statements derived from models should be based on compounding the probability from the model with the probability that the model itself is a correct representation of the world. Certain forecasts are just not possible.



Topics:  Frontiers of economic research

Tags:  probalistic reasoning, predictions

Fellow of St John’s College, Oxford


CEPR Policy Research