August 20, 2013


Diversity edition

  • Statistical classification (data mining, learning) algorithms will learn to match your classifications. Sometimes that’s not quite what you want
  • People are starting to comment more on entirely-male conference speaker lineups. Here’s a simple calculator for the probability distribution of number of people from some group (eg women), for a given proportion in the target population. For example, if you select 10 people from a population that’s 15% female, you should have only a 1/9 chance of not getting any women.
  • Map of scientific collaborations, based on co-authorship of books and papers. (click for a really big version)




Thomas Lumley (@tslumley) is Professor of Biostatistics at the University of Auckland. His research interests include semiparametric models, survey sampling, statistical computing, foundations of statistics, and whatever methodological problems his medical collaborators come up with. He also blogs at Biased and Inefficient See all posts by Thomas Lumley »

Add a comment

First time commenting? Please use your real first name and surname and read the Comment Policy.