- Week 2 Overview
- Two Main Ways to Study Cause and Effect
- The Classical Paradigm
- Potential Outcomes Paradigm
- Traditional Statistics vs. Causal Inference
- Potential Outcomes vs. Classical Paradigms
- Foundational Concepts
- The Classical Paradigm
- Potential Outcomes Paradigm
- Strength
- Consistency
- Specificity
- Timing
- Gradient
- Plausibility
- Coherence
- Analogy
- Experimental Evidence
- Observation
- Gather More Information
- Apply Bradford Hill Criteria
- Make a Judgment
- Gathering Evidence
- Review by Authorities
- Judging the Evidence
- Final Statement
- Think of Possible Outcomes
- How Are Treatments Given
- Model for The Science
- What Statistics Usually Does: Associational Inference
- What Causal Inference Usually Does
- What is the Cause?
- What is the Effect?
- Objects of Study
- Statistical Population
- Key Variables
- Definition
- Thinking Experimentally
- Key Feature
- Contrast with Attributes
- Role of Time
- Experimental Treatments as Causes
- Relative Effects
- Not Limited to Randomized Studies
- (Y^t_i), (Y^c_i), (Y^Z_i)
- Innate Characteristics Before Treatment
- Assignment to (Z) Determines Observed Outcome
- Relationship Between Potential Outcomes and Observed Data