Monday, February 28, 2011

Directionally Challenged

Why was the statistician always getting lost?


Too many random walks.



1 comment:

  1. A random walk is a statistical model where the value that a variable takes today is equal to its value yesterday plus an error term. This means that our best prediction of tomorrow's value is today's value.
    Another property of a random walk is that its variance increases as the process evolves. In the example above, this means that the variance of the location of the statistician increases the longer he walks.

    ReplyDelete