Archive for Zipf’s Law

power laws, or not

Posted in Statistics, University life with tags , , on February 10, 2012 by xi'an

Michael Stumpf and Mason Porter just published a column in Science entitled Critical truths about power laws.  I find this column quite interesting in that it criticises the attraction people feel for the “universality” of power laws. The paper lists a range of areas and corresponding papers where power laws have been exhibited, with or without statistical significance, but the interpretation of the resulting power law is often lacking! I quite agree with this critical analysis against the temptation to find a simple all-fitting family of distributions, the “vague and mistakenly mystical sense of universality” the paper conclude with. (Zipf’s law, which pops up at each controversial election, appears in the list of well-supported fits, but I cannot trace a reference in the paper.)