Lars Peter Hansen, the Nobel Laureate in the Middle - NYTimes.com - 0 views
-
The Nobel committee recognized Professor Hansen this year for developing a statistical technique, the generalized method of moments. He described it as “a method that allows you to do something without having to do everything.” For example, it’s still impossible to come up with a complete and entirely coherent model of either the overall economy or financial markets, to say nothing of combining the two. But his methods help make it possible to study some of the elements and connections in a statistically valid way. “The idea is to make progress,” he said, “even if you can’t do it all now.” And his approach is in wide use in other areas of social science.
-
The science of economic model-building is very much a work in progress, he said. “The thing to remember about models is they’re always approximations and they will always turn out to be wrong,” he said. That shouldn’t be a surprise, he said, and it doesn’t mean that the models are useless. “You need to ask, are the models wrong in ways that are central to the questions you want to ask, or are they wrong in ways that aren’t so central?” The important thing is to make them better and to come up with interesting answers, he said.
-
Prevailing economic models do not adequately explain the financial crisis, the severe recession or the weak global recovery, he said. “Systemic risk” is a buzzword for politicians and financial regulators, he said, but “the truth is, we really don’t know how to measure it or what exactly it is.”
- ...2 more annotations...
-
“If you simply announce that things are irrational, then that alone doesn’t get you very far. You have to replace rational agents with some concrete notion of what it means to be irrational.” You need to test that notion in a formal, mathematical model, he said. Some of his students have been working at this. “As long as they’re doing this in formal and rigorous ways, I’m all in favor of it.”
-
He’s at work, with other scholars, to improve the quality of such models, with the hope “that in five or 10 years we’ll have much better answers.” Not complete answers, but better ones.