Less Wrong is a community blog devoted to refining the art of human rationality. Please visit our About page for more information.

JohnH comments on Occam's Razor - Less Wrong

37 Post author: Eliezer_Yudkowsky 26 September 2007 06:36AM

You are viewing a comment permalink. View the original post to see all comments and the full post content.

Comments (52)

Sort By: Old

You are viewing a single comment's thread. Show more comments above.

Comment author: JohnH 22 April 2011 03:32:05AM 2 points [-]

In statistics generally the model that has the least variables and is the most statistically probable is the one used. See things like AIC or Bayesian Information Criterion on how to choose a good model. This means that Occam's razor is accurate. Given that is is possible to continuously add variables to a model and get a perfect fit but have the model be blown apart with the addition of an additional observation that is not otherwise influential, then, unless you are defining probability to include an Information Criterion, your formulation is less useful.