Logistic Regression And Binary Outcomes

Teach binary outcome modelling separately from linear regression.

Units

1. Unit 10.00: Why a straight line fails on a 0/1 outcome
2. Unit 10.01: From bounded to unbounded
3. Unit 10.02: The family argument is the whole difference
4. Unit 10.03: Multiplies the odds, not the risk
5. Unit 10.04: Predict on the link scale, convert afterwards
6. Unit 10.05: 95% accuracy can mean catching nothing
7. Unit 10.06: Calibration is the model's job; the threshold is yours

Module work

• Activity
• Knowledge check
• Summary