Let’s imagine you’re incredibly lazy and you want to learn R, but you only want to learn one function to do statistics. What function do you learn? I’d recommend to learn to use the lm() function. Why? Because most common statistical tests are in fact nothing more than some variation of a linear model, from the simplest One-Sample T-test to a repeated-measures ANOVA. I think most people that have Googled for this question have found Jonas Lindeløv’s post on how common statistical tests are linear models (as they should, it’s an amazing post). Here I want to go a bit more in depth into the mathematics behind this statement to show how common statistical tests are in fact variations of a linear model.
This page cannot be shown here. You can still read it on the original site — the toolbar below keeps your place in the directory.
Let’s imagine you’re incredibly lazy and you want to learn R, but you only want to learn one function to do statistics. What function do you learn? I’d recommend to learn to use the lm() function. Why? Because most common statistical tests are in fact nothing more than some variation of a linear model, from the simplest One-Sample T-test to a repeated-measures ANOVA. I think most…
Comments
Nothing yet. Say the first thing.
Sign in to join the conversation.