Crash Course Statistics: Understanding model output and testing in R
You had a stats introduction before (maybe some time ago) and know how to run a linear model in R, e.g. “lm(y~a+b)”. But you got a little bit rusty on interpreting the model output? You ask yourself: What do these t-test and F-tests tell you? What is a post-hoc test? Why is there a difference between covariates and factors? How is an interaction treated?
Don’t worry, we will bring you up to date without you having to dedicate a whole week. Based on an empirical dataset, we will recap reading model output and perform model testing for LM, ANOVA, ANCOVA, LMM (and some brief outlook on GLM).
At the end of this short workshop, you will have learned how to understand model output of R-functions lm(), aov(), and lmer(). You will be prepared for testing hypotheses based on your own datasets.
Benjamin did his PhD in Applied Mathematics and is a postdoc in the ‘Theory in Biodiversity’ group. He has several years of experience in ecological modeling as well as math and stats consultation. His research focusses on statistical methods for population dynamics.