I can claim that in talking about modern economics I am talking about me. My finger has been in every pie. I once claimed to be the last generalist i… - Paul Samuelson

A later writer, such as Leijonhufvud, I knew to have it wrong, when he later argued the merits of Keynes’s subtle intuitions and downplayed the various (identical!) mathematical versions of The General Theory. The so-called 1937 Hicks or later Hicks–Hansen IS–LM diagram will do as an example for the debate.

Econometrics may be defined as the quantitative analysis of actual economic phenomena based on the concurrent development of theory and observation, related by appropriate methods of inference.

Well, I'd say, and this is probably a change from what I would have said when I was younger: Have a very healthy respect for the study of economic history, because that's the raw material out of which any of your conjectures or testings will come. And I think the recent period has illustrated that. The governor of the Bank of England seems to have forgotten or not known that there was no bank insurance in England, so when Northern Rock got a run, he was surprised. Well, he shouldn't have been.
But history doesn't tell its own story. You've got to bring to it all the statistical testings that are possible. And we have a lot more information now than we used to.