tag:blogger.com,1999:blog-987850932434001559.post5340395963291117807..comments2022-01-20T14:32:04.408+01:00Comments on The 20% Statistician: P-values vs. Bayes FactorsDaniel Lakenshttp://www.blogger.com/profile/18143834258497875354noreply@blogger.comBlogger1125tag:blogger.com,1999:blog-987850932434001559.post-80448171946676053852021-09-02T15:47:25.802+02:002021-09-02T15:47:25.802+02:00Hi all,
you don't have to be a proponent of t...Hi all, <br />you don't have to be a proponent of the Neyman-Pearson approach to use p-values or power. All that is required is that you pit two models against each other: one for the null hypothesis of interest and one for a specific alternative hypothesis. A statistical criterion then gives you p and beta as conditional probabilities under the model assumptions. There is no need to interpret them as long-term error probabilities because there is no need to make inferences past the data and the model. -- So what is my goal of a statistical test? Not to make inferences about future tests or about a platonic "population", but simply to safeguard against chance by comparing models. Thinking of tests more in terms of "evaluation" than of "decision" turns p and beta into useful, standardized measures of data quality, and all the metaphysics of populations, true values, infinite experiments, long term errors and so on (all quite bizarre from an ontological point of view) is out of the window.Anonymoushttps://www.blogger.com/profile/06880761681096663210noreply@blogger.com