In 2018, I wrote a post about a data visualisation showing that the age you consider ‘old’ is the square root of your age times 8. So if you are 25 you will consider 40 to be old. In brief, my main problem with the data visualisation was the low N (~200), i.e., the small […]
Category: statistics
How to improve your figures #9: Use colourblind-friendly colours
Colours are often used in data visualisations to emphasise variation, ease interpretation and make them aesthetically pleasing. However, we do not all see colours in the same way and you should take this fact into account when you design figures. Specifically, as a start, you should make sure that everybody can actually see the variation […]
Årets første sommerdag
På Twitter delte DMI en figur med information om, hvornår vi hvert år i perioden 2005 til 2022 har haft årets første sommerdag (en maksimumtemperatur på over 25 °C). Figuren kan ses her: Jeg var ingenlunde imponeret over denne figur og ville sågar kalde den problematisk. Generelt har jeg det svært med figurer, der formidler […]
Potpourri: Statistics #84
1259. Introduktion til R 1260. Improving Your Statistical Inferences 1261. Dataviz Inspiration 1262. A guide to modeling outcomes that have lots of zeros with Bayesian hurdle lognormal and hurdle Gaussian regression models 1263. The Effects of Regularization and Data Augmentation are Class Dependent 1264. latentcor: An R Package for estimating latent correlations from mixed data […]
Experiments and societal challenges
The randomised controlled trial is seen as the gold standard within the social sciences. I do not disagree. I love well-executed experiments with strong causal identification. If two studies, one experimental and one non-experimental, differ in their conclusions, there is no doubt which study I, all else equal, will side with. Most importantly, I often […]