I view the work I've done related to statistics and economics as roughly speaking, how to do something without having to do everything. So economic models — how any model by definition isn't right. When someone just says, 'Oh, your model is wrong.' That's not much of an insight. What you want to know is, is wrong in important ways or wrong in ways that are less relevant? And you want to know what does the data really say about the model?

In: David Brancaccio (2013) "Nobel Prize in Economics winner Lars Peter Hansen on imperfect models" at marketplace.org.