Unknown unknowns…


When I want to explain the concept of Knightian uncertainty (Frank Knight, 1921) to my students. I sometimes refer to the video filmed in March 2003 of Donald Rumsfeld, former U.S. Defense Secretary, where he talks unknown unknowns – the ones we don’t know we don’t know – during a press conference in Baghdad… In the sense of Knight, some future outcomes will ever remain unknown unknowns, as if a part of our Future will remain hidden. Consequently, we cannot build a probability density function to forecast future outcomes. We simply cannot and do not know. Do Knightian uncertainty really exist in real life? This is the fundamental question.