(Photo by Steven Kamenar on Unsplash) The Random Forest algorithm is often said to perform well “out-of-the-box”, with no tuning or feature selection needed, even with so-called high-dimensional data, where we have a high number of features (predict...

(Image is from a different antigen test) Many people are suspicious about the reliability of rapid self-tests, so I decided to check it out. For starters, I LOVE measurement. It is where learning from data starts, with technology and statistics inv...

Gertjan Verhoeven & Misja Mikkers Here we show how to use Stan with the brms R-package to calculate the posterior predictive distribution of a covariate-adjusted average treatment effect. We fit a model on simulated data that mimics a (very c...