Question
Judea Pearl pioneered the use of directed acyclic graphs, or DAGs, for studying this relationship. For 10 points each:
[10e] Name this relationship often quantified via treatment effects. Randomized controlled trials are the gold standard in a field devoted to inference about this relationship.
ANSWER: causality [or causation; accept word forms such as cause; accept causal inference]
[10m] In a type of analysis named for these features, causal effects on a DAG can be computed by summing products of coefficients named for these features. The adoption of the QWERTY keyboard as the standard is a classic example of a “dependence” on these features in economics.
ANSWER: paths [accept path analysis; accept path coefficients; accept path dependence]
[10h] Independent variables in a DAG can be made dependent by conditioning on one of these variables, so named because two arrows point into them. Berkson’s paradox exemplifies a form of bias named for these variables, in which controlling for one of them induces spurious correlations.
ANSWER: colliders [accept collider bias]
<Morrison, Social Science>
Summary
| 2024 ESPN @ Stanford | 03/09/2024 | Y | 2 | 15.00 | 100% | 50% | 0% |
| 2024 ESPN @ Brown | 04/06/2024 | N | 3 | 10.00 | 67% | 33% | 0% |
| 2024 ESPN @ Cambridge | 04/06/2024 | N | 2 | 15.00 | 100% | 50% | 0% |
| 2024 ESPN @ Chicago | 03/23/2024 | N | 6 | 10.00 | 83% | 17% | 0% |
| 2024 ESPN @ Columbia | 03/23/2024 | N | 6 | 15.00 | 83% | 50% | 17% |
| 2024 ESPN @ Duke | 03/23/2024 | N | 2 | 15.00 | 100% | 50% | 0% |
| 2024 ESPN @ Online | 06/01/2024 | N | 3 | 13.33 | 67% | 67% | 0% |
Data
| Stanford | Berkeley A | 10 | 0 | 0 | 10 |
| Free Agents | Berkeley B | 10 | 10 | 0 | 20 |