Skip to content


Standard Deviation

The notion of standard deviation has confused hordes of scientists; it is time to retire it from common use and replace it with the more effective one of mean deviation. Standard deviation, STD, should be left to mathematicians, physicists and mathematical statisticians deriving limit theorems. There is no scientific reason to use it in statistical investigations in the age of the computer, as it does more harm than good—particularly with the growing class of people in social science mechanistically applying statistical tools to scientific problems.

Say someone just asked you to measure the “average daily variations” for the temperature of your town (or for the stock price of a company, or the blood pressure of your uncle) over the past five days. The five changes are: (-23, 7, -3, 20, -1). How do you do it?



  1. Certainly, we need better instruments to handle this more random world, in spite of the conflation of the two deviations by scientist. I like the 80/20 distribution, and ratio of 1/n as they demonstrate the properties of fat tails, the infinite variance notion is hunting though.

    Tuesday, January 21, 2014 at 11:29 am | Permalink
  2. Chuck Morefield wrote:

    Perhaps a small oversight in words used to describe the number for SD? Dr. Taleb showed SD as ~15.7, which uses an n-1 normalization. But his actual words seem to describe an n normalization (which would result in ~14.05). I.e. his words in Edge reflect his 2007 paper, which used n, but his actual SD number in Edge reflects n-1. Not a big deal, I liked his comments as usual.

    Friday, May 20, 2016 at 2:31 pm | Permalink

Post a Comment

Your email is never published nor shared. Required fields are marked *