module 12

# Module 12 Flashcards

### Causation and Explanation

Q: What is causation?

A: Causation refers to a relationship where one event (the cause) directly influences another event (the effect).

Q: What role does explanation play in understanding causation?

A: Explanation helps clarify how and why a causal relationship exists, linking causes to their effects logically or empirically.

---

### The Problem with “Seeing” Causation

Q: Why is causation difficult to “see”?

A: Causation cannot be directly observed; it must be inferred from patterns, correlations, and controlled experiments.

Q: What common mistake arises from assuming causation?

A: Confusing correlation with causation, leading to erroneous conclusions about relationships between variables.

---

### Probability and Causation

Q: How does probability relate to causation?

A: Probabilistic reasoning can suggest causal relationships by showing how changes in one variable affect the likelihood of another.

Q: What is probabilistic causation?

A: A concept where a cause increases the probability of its effect but does not guarantee it.

---

### Probabilistic (In)Dependence

Q: What is probabilistic independence?

A: Two variables are independent if the occurrence of one does not affect the probability of the other.

Q: What is probabilistic dependence?

A: A situation where the probability of one event is influenced by the occurrence of another.

---

### Correlation and Causation

Q: What is the difference between correlation and causation?

A: Correlation is a statistical relationship between variables, while causation implies a direct cause-and-effect link.

Q: Why does correlation not imply causation?

A: Correlation can arise from confounders, coincidence, or other indirect relationships.

---

### Common Cause Principle

Q: What is the common cause principle?

A: If two variables are correlated, there is often a common cause influencing both.

Q: Why is identifying a common cause important?

A: It prevents misattribution of causation to one variable when another variable is the true cause.

---

### Confounders

Q: What is a confounder?

A: A variable that influences both the independent and dependent variables, potentially distorting the perceived relationship.

Q: How can confounders be controlled?

A: Through randomization, matching, or statistical adjustments in experiments.

---

### Screening Off

Q: What is the concept of screening off?

A: When a common cause makes two variables independent, the knowledge of one variable does not provide additional information about the other.

Q: Provide an example of screening off.

A: If smoking (common cause) explains both tar in lungs and lung cancer, knowing about tar does not add extra predictive value once smoking is known.

---

### Spurious Correlation

Q: What is spurious correlation?

A: A correlation between variables that arises due to coincidence or a hidden factor, not a causal relationship.

Q: Provide an example of spurious correlation.

A: The correlation between ice cream sales and drowning rates (linked by the hidden variable of hot weather).

---

### Randomized Control Tests (RCTs)

Q: What is an RCT?

A: A study design where participants are randomly assigned to groups to test causal relationships while minimizing bias.

Q: Why are RCTs considered the gold standard in causal inference?

A: They reduce confounders and ensure that observed effects are due to the intervention.

---

### Simpson’s Paradox

Q: What is Simpson’s Paradox?

A: A phenomenon where a trend appears in individual groups but reverses when data is combined.

Q: Provide an example of Simpson’s Paradox.

A: A treatment appears effective in separate gender groups but ineffective when genders are combined due to differing group sizes.

---