The Importance of Predicting Causal Factors

Bob Greene: It's obvious you can't do experiments with history. We don't have time machines. But I think it's salutary to think about, he says. He asks what framework would be used to assess super forecasters who make a prediction. Would they take the subset that are more accurate on the observed branch of history and say those were likely to be more accurate in the predictions on the counterfactual branch? "I don't know," said Greene. 'That's just what happens when you can do experiments'