causal-inference-studies
Explaining the main concepts around causal learning via bitesize theory and code!
The notebooks can be found on this page 💻, whereas the lessons are listed below 👇.
Introduction
| Number | Lesson | Complexity |
|---|---|---|
| 01 | Why causality matters | 🟢 |
| 02 | When regression goes wrong | 🟢 |
| 03 | When regression goes wrong 2 | 🟢 |
| 04 | Defining causation | 🟢 |
| 05 | Non-causal problems | 🟢 |
Core concepts
| Number | Lesson | Complexity |
|---|---|---|
| - | Potential Outcomes | 🟡 |
| - | DAGs - Expressing causal knowledge | 🟡 |
| - | DAGs - Basic math | 🟡 |
| - | Insights from DAGs | 🟡 |
| - | Causal effect Identification | 🟡 |
| - | Types of causal effects | 🟡 |
Advanced topics
| Number | Lesson | Complexity |
|---|---|---|
| - | Simpson's paradox | 🟡 |
| - | DAGs with math | 🔴 |
| - | Attribution | 🔴 |
| - | Causal assumptions | 🟡 |
| - | A/B testing | 🟡 |
| - | Causality and time | 🔴 |
| - | Shapley values | 🟡 |
| - | Shapley cont'd | 🟡 |
Complexity score:
- 🟢: a piece of cake
- 🟡: requires thinking about it, involves some math
- 🔴: requires connecting dots, it's more rigorous
If you need a quick refresher on probability, check out this page.
External material such as books, video lectures, repos and Python packages are listed here.