(Mis)using Bayes

Dean Radin observed that, "Skeptics jump on Bayesian methods as a convenient way to explain away psi effects, because they can conveniently choose priors that do not allow any new data to shift their initial position. In this way Bayesian methods mathematically prove why orthodoxy persists until the holders of the status quo die."

Brian Josephson remarked on the similarity to Max Planck's famous quote: "A new scientific truth does not triumph by convincing its opponents and making them see the light, but rather because its opponents die and a new generation grows up that is familiar with it." This has been paraphrased as 'science advances funeral by funeral'.

Dean's response: "Not only was Planck provably correct, but we can calculate that as certain people die (the current more visible holders of the status quo), that the Bayesian likelihood that psi is real will progressively increase. And the beauty is that this will happen without any of us having to generate any new data at all."


A valuable new paper (2011), written by Daryl Bem, Jessica Utts, and Wes Johnson, explains how two apparently well developed statistical approaches can, disconcertingly, give wildly different answers about the evidence from clean, well-designed experimental research. The paper is a response to a critique of a paper by Bem which reports evidence of precognitive effects in several psychological paradigms with the temporal order of actions and feedback reversed. The paper can be downloaded from http://dl.dropbox.com/u/8290411/ResponsetoWagenmakers.pdf  It also provides, in the references, access information for the original papers.


Comments