I recently developed an interest in Bayesian statistics, or more specifically, Bayesian hypothesis testing. One of the the cool things about the Bayesian approach is that it allows us to accept the null hypothesis. Or more precisely, it allows us to quantify the relative evidence (provided by the data) in favor of the null hypothesis, as compared to the alternative hypothesis (or the other way around). Of course, this is impossible under the frequentist approach where we can only reject the null hypotheis. Since I am apparently one of the very few researchers doing Bayesian stuff at my Department, I was asked to give an introductory talk for a group of PhDs on this topic. So here I am, talking Bayes and wearing Bayes.

Geef een reactie

Het e-mailadres wordt niet gepubliceerd.