A post from blogger Agnostic at Gene Expression asks whether the use of information criteria -- that is, how well an observation fits a statistical model with given hypotheses -- is beginning to replace p-values. While the community leans heavily on p-values, Agnostic notes that these measures are limited by their connection to a null hypothesis: "They do not allow us to decide which of a variety of hypotheses or models is true." Agnostic ran a literature search and found that while p-values are still far more common, the use of information criteria models is increasing. "The writing is on the wall," Agnostic blogs. "Aside from being intellectually superior, information criteria will give you a competitive edge in the job market, at least in the near future. After that, they will be required."
Just What You Needed: More Stats to Learn
Mar 06, 2009