Week 5 - Simple Regression
The Linear Model
Last week ended with a trick question. You ran a t-test, you ran a correlation, and then you ran lm() — and the numbers came back the same. That was not a coincidence, and this week we find out why.
Here is the idea the rest of the course rests on: almost everything we do is a line through data. A group difference is a line. A correlation is a line. Regression is not a new topic sitting next to t-tests and correlations — it is the general machine that those tests are special cases of. Once you can read a line, you can read most of a results section.
So this week we slow down on three numbers: the intercept (where the line starts), the slope (how steeply it climbs), and the residual (how wrong the line is for one particular person). We’ll fold in correlation and effect size along the way, because r and R² are just other ways of asking how much the line helps.
You are about to meet a lot of intercepts that are nonsense — the predicted number of Transformers movies for a person aged zero, the price of a LEGO set with no pieces. That is fine and expected. Part of reading a model well is knowing which of its numbers you are allowed to take seriously.
Prepare
Slides
💻 Simple Regression: The Linear Model
Both decks cover the same concepts with the same data and the same numbers - one drives R, the other drives JAMOVI. Pick whichever you want to get better at. The in-class activity gives every step both ways, and the JAMOVI deck ends with a side-by-side cheat sheet.
Data
Data comes from Cards Against Humanity: Pulse of the Nation, a monthly public opinion poll that asked a national sample some genuinely strange questions.
In-Class Activity
For Next Time
📋Lab 6 - Reading the Line — due Tuesday 9/29 at 11:59pm
The lab schedule has shifted from the version in the PDF syllabus. Lab 6 is due 9/29, a week earlier than the PDF says, and the midterm project will be assigned on 10/15 and due 10/27. The course website is the current version — I will walk through the full revised schedule in class.
Back to course schedule ⏎