[G1-Sync] Manual knowledge update

This commit is contained in:
Antigravity Agent
2026-05-10 22:08:15 +09:00
parent 21ac3ed255
commit 504fd5fb42
3011 changed files with 380280 additions and 206977 deletions
+284 -39
View File
@@ -2,62 +2,307 @@
id: wiki-2026-0508-causal-inference
title: Causal Inference
category: 10_Wiki/Topics
status: needs_review
status: verified
canonical_id: self
aliases: [CAUSAL-001]
aliases: [인과 추론, causal inference, do-calculus, Pearl, DAG, counterfactual, SCM, RCT, propensity score]
duplicate_of: none
source_trust_level: A
confidence_score: 1.0
tags: ["Statistics|[Statistics", ai, causal-inference, causality, counterfactuals]
confidence_score: 0.93
verification_status: applied
tags: [statistics, causal-inference, dag, do-calculus, pearl, ab-testing, dowhy, econml, observational-study]
raw_sources: []
last_reinforced: 2026-04-26
last_reinforced: 2026-05-10
github_commit: pending
inferred_by: Claude Opus 4.7 (auto-normalize 2026-05-08)
tech_stack:
language: Python / R
framework: DoWhy / EconML / CausalML / pgmpy
---
# Causal Inference (인과 추론)
# Causal Inference
## 📌 한 줄 통찰 (The Karpathy Summary)
> "상관관계(Correlation)에 속지 말고, 진짜 원인(Cause)을 파헤쳐라" — 단순히 두 현상이 함께 일어나는지 관찰하는 것을 넘어, 한 변수의 변화가 다른 변수의 변화를 실제로 유발하는지 통계적/논리적으로 추론하는 과정.
## 📌 한 줄 통찰
> **"매 correlation 의 X — 매 cause"**. 매 Judea Pearl 의 ladder. 매 observational 의 limit + 매 RCT / DAG / counterfactual 의 fix. 매 modern AI 의 base capability — 매 LLM 의 weakest area. 매 policy / medical / business 의 critical.
## 📖 구조화된 지식 (Synthesized Content)
- **추출된 패턴:** 관측 데이터 뒤에 숨겨진 구조적 인과 모델(SCM)을 설정하고, "만약 A가 일어나지 않았다면 어떠했을까?"라는 반사실적(Counterfactual) 질문을 통해 인과 효과를 산출하는 분석 패턴.
- **주요 도구:**
- **Directed Acyclic Graphs (DAGs):** 변수 간의 인과 경로를 시각화.
- **Do-calculus:** 개입(Intervention)이 일어났을 때의 확률 분포 변화를 계산 (주디아 펄).
- **Instrumental Variables:** 관찰되지 않은 혼란 변수(Confounder)를 통제하기 위한 기법.
- **의의:** 데이터 기반 AI가 범하기 쉬운 "닭이 울어서 해가 뜬다"식의 오류를 방지하고, 정책 결정이나 의학적 진단에서 신뢰할 수 있는 가이드라인 제공.
## 📖 핵심
## ⚠️ 모순 및 업데이트 (Contradictions & Updates)
- **과거 데이터와의 충돌:** 빅데이터가 모든 답을 줄 것이라 믿었던 시기에서, 데이터의 양보다 데이터가 생성된 '구조'가 더 중요하다는 사실을 깨닫는 과정.
- **정책 변화:** Antigravity 프로젝트는 시스템 장애 분석 시 단순 통계적 상관관계 대신 인과 추론 방법론을 적용하여, 장애의 진짜 원인을 타격하는 해결책을 제시함.
### Pearl's Ladder of Causation
1. **Association** (P(y|x)): 매 correlation. 매 standard ML.
2. **Intervention** (P(y|do(x))): 매 "what if I change x?".
3. **Counterfactual** (P(y_x|x', y')): 매 "what would have happened if?".
## 🔗 지식 연결 (Graph)
- Root-Cause-Analysis-RCA, [[Probabilistic-Graphical-Models|Probabilistic-Graphical-Models]], Bayesian-Inference, Decision-Making
- **Raw Source:** 10_Wiki/Topics/AI/Causal-Inference.md
→ 매 LLM 의 mostly stuck on step 1.
## 🤖 LLM 활용 힌트 (How to Use This Knowledge)
### 매 핵심 concept
**언제 이 지식을 쓰는가:**
- *(TODO)*
#### Confounder
- 매 X → Y 매 spurious 의 매 Z (common cause).
- 예: 매 ice cream sales ↔ drowning (Z = 매 summer).
**언제 쓰면 안 되는가:**
- *(TODO)*
#### Mediator
- 매 X → M → Y.
## 🧪 검증 상태 (Validation)
#### Collider
- 매 X → Z ← Y.
- 매 Z 의 condition 의 spurious correlation 의 induce!
- **정보 상태:** needs_review
- **출처 신뢰도:** A
- **검토 이유:** *(P-Reinforce Phase 1 자동 정규화. 본문 검증 필요.)*
#### Backdoor path
- 매 X ← Z → Y.
- 매 Z 의 control 의 close.
## 🧬 중복 검사 (Duplicate Check)
#### Frontdoor
- 매 X → M → Y (매 confounder 가 매 X-Y 간 의 unobserved).
- **기존 유사 문서:** *(TODO: 인덱서 클러스터 리포트 참조)*
- **처리 방식:** UPDATE (자동 정규화)
- **처리 이유:** Phase 1 정규화 — 옛 템플릿/누락 필드 보강.
### 매 method
## 🕓 변경 이력 (Changelog)
#### RCT (gold standard)
- 매 randomization 의 confounder 의 break.
- 매 ethics / cost.
| 날짜 | 변경 내용 | 처리 방식 | 신뢰도 |
|------|-----------|-----------|--------|
| 2026-05-08 | P-Reinforce Phase 1 정규화 (frontmatter + 헤더 표준화) | UPDATE | A |
#### Observational + adjustment
- **Propensity Score Matching (PSM)**.
- **Inverse Probability Weighting (IPW)**.
- **Regression discontinuity (RDD)**.
- **Difference-in-differences (DiD)**.
- **Instrumental variables (IV)**.
- **Synthetic control**.
#### Causal graph (DAG)
- 매 explicit assumption.
- 매 do-calculus 의 identify.
#### ML-based
- **Causal forest** (Wager-Athey).
- **Double ML** (Chernozhukov).
- **CausalGAN / counterfactual VAE**.
### 매 Simpson's paradox
- 매 aggregate vs subgroup 의 reverse.
- 매 Berkeley admission, 매 kidney stone treatment.
- → 매 confounder 의 stratify.
### 매 응용
1. **A/B test** + 매 follow-up causal.
2. **Pricing**: 매 price → 매 demand.
3. **Marketing attribution**: 매 channel → 매 conversion.
4. **Medicine**: 매 treatment effect.
5. **Policy**: 매 minimum wage.
6. **Education**: 매 program effect.
7. **Recommender**: 매 click ≠ 매 caused conversion.
### 매 modern tool
- **DoWhy** (Microsoft): 매 4-step framework.
- **EconML** (Microsoft).
- **CausalML** (Uber).
- **pgmpy**: 매 graphical model.
- **GeNIe / Hugin**: 매 visual.
- **DAGitty**: 매 web DAG.
### 매 LLM 의 한계
- 매 association 의 strong.
- 매 spurious 의 confidently 의 emit.
- 매 causal reasoning 의 weak.
- 매 hybrid (LLM + symbolic causal) 의 trend.
## 💻 패턴
### DoWhy (4-step framework)
```python
from dowhy import CausalModel
model = CausalModel(
data=df,
treatment='ad_exposure',
outcome='conversion',
common_causes=['age', 'income', 'past_purchases'],
)
# 1. Identify
estimand = model.identify_effect(proceed_when_unidentifiable=False)
print(estimand)
# 2. Estimate
estimate = model.estimate_effect(estimand, method_name='backdoor.propensity_score_matching')
print(estimate.value)
# 3. Refute
refutation = model.refute_estimate(estimand, estimate, method_name='placebo_treatment_refuter')
print(refutation)
```
### Propensity Score Matching
```python
from sklearn.linear_model import LogisticRegression
from sklearn.neighbors import NearestNeighbors
# 매 propensity score = P(treatment=1 | covariates)
ps_model = LogisticRegression()
ps_model.fit(X_covariates, treatment)
ps = ps_model.predict_proba(X_covariates)[:, 1]
# 매 match treated to control
treated = df[df.treatment == 1]
control = df[df.treatment == 0]
knn = NearestNeighbors(n_neighbors=1).fit(ps[control.index].reshape(-1, 1))
matches = knn.kneighbors(ps[treated.index].reshape(-1, 1), return_distance=False)
# 매 ATE estimate
ate = treated.outcome.mean() - control.iloc[matches.flatten()].outcome.mean()
```
### IPW (Inverse Probability Weighting)
```python
def ipw_ate(df, treatment, outcome, ps):
weight = np.where(df[treatment] == 1, 1 / ps, 1 / (1 - ps))
treated_avg = (df[outcome] * df[treatment] * weight).sum() / weight[df[treatment] == 1].sum()
control_avg = (df[outcome] * (1 - df[treatment]) * weight).sum() / weight[df[treatment] == 0].sum()
return treated_avg - control_avg
```
### Difference-in-Differences (DiD)
```python
import statsmodels.api as sm
# 매 panel data: pre/post × treatment/control
df['post'] = (df['period'] >= treatment_period).astype(int)
df['treated'] = (df['group'] == 'treated').astype(int)
df['interaction'] = df['post'] * df['treated']
model = sm.OLS(df['outcome'], sm.add_constant(df[['post', 'treated', 'interaction']])).fit()
# 매 interaction coefficient = 매 DiD treatment effect
print(model.summary())
```
### Causal Forest (heterogeneous treatment effect)
```python
from econml.dml import CausalForestDML
cf = CausalForestDML(
n_estimators=200,
discrete_treatment=True,
random_state=42,
)
cf.fit(Y=df['outcome'], T=df['treatment'], X=df[features], W=df[confounders])
# 매 individual treatment effect
ites = cf.effect(df_test[features])
# 매 confidence interval
lower, upper = cf.effect_interval(df_test[features], alpha=0.05)
```
### DAG + Pearl's do-calculus (pgmpy)
```python
from pgmpy.models import BayesianNetwork
from pgmpy.factors.discrete import TabularCPD
from pgmpy.inference.CausalInference import CausalInference
# 매 X → Y, X → Z → Y
model = BayesianNetwork([('X', 'Y'), ('X', 'Z'), ('Z', 'Y')])
# ... add CPDs ...
ci = CausalInference(model)
# 매 P(Y | do(X = 1))
result = ci.query(variables=['Y'], do={'X': 1})
print(result)
```
### Synthetic control (state policy effect)
```python
# 매 weighted combination of control units 의 treated 의 mimic
from synthetic_control import SyntheticControl # 매 hypothetical lib
sc = SyntheticControl(
treated_unit='California',
control_pool=other_states,
pre_period=range(1990, 2000),
post_period=range(2000, 2010),
)
sc.fit(predictors=['gdp', 'unemployment', 'income'])
effect = sc.treatment_effect()
```
### Refutation (sensitivity analysis)
```python
from dowhy import CausalModel
# 1. Placebo treatment
refute_placebo = model.refute_estimate(
estimand, estimate, method_name='placebo_treatment_refuter',
)
# 매 effect 의 0 가까이 → 매 robust.
# 2. Random common cause
refute_random = model.refute_estimate(
estimand, estimate, method_name='random_common_cause',
)
# 3. Data subset
refute_subset = model.refute_estimate(
estimand, estimate, method_name='data_subset_refuter',
)
```
### Simpson's paradox detector
```python
def detect_simpson(df, x_col, y_col, group_col):
# 매 aggregate
overall_corr = df[[x_col, y_col]].corr().iloc[0, 1]
# 매 subgroup
subgroup_corrs = df.groupby(group_col).apply(
lambda g: g[[x_col, y_col]].corr().iloc[0, 1]
)
if overall_corr > 0 and (subgroup_corrs < 0).all():
return f"Simpson's paradox: overall +, subgroups all -"
if overall_corr < 0 and (subgroup_corrs > 0).all():
return f"Simpson's paradox: overall -, subgroups all +"
return None
```
## 🤔 결정 기준
| 상황 | Method |
|---|---|
| New feature launch | A/B test (RCT) |
| Historical data | DoWhy + matching |
| Heterogeneous effect | Causal Forest |
| Panel data | DiD |
| Cutoff threshold | RDD |
| Hidden confounder + IV | Instrumental Variables |
| Single treated unit | Synthetic Control |
| ML-aware confounder | Double ML |
**기본값**: 매 RCT first. 매 observational 가 DoWhy + sensitivity refute.
## 🔗 Graph
- 부모: [[Statistics]] · [[Decision-Theory]] · [[Epidemiology]]
- 변형: [[DAG]] · [[Do-Calculus]] · [[Counterfactual]] · [[Structural-Causal-Model]]
- 응용: [[A-B-Testing]] · [[Marketing-Attribution]] · [[Treatment-Effect]] · [[Policy-Evaluation]]
- Tool: [[DoWhy]] · [[EconML]] · [[CausalML]] · [[pgmpy]]
- Adjacent: [[Bayesian-Statistics]] · [[Anthropic-Principle]] · [[Beliefs]] · [[Algorithmic-Fairness]]
## 🤖 LLM 활용
**언제**: 매 policy decision. 매 marketing attribution. 매 medical treatment. 매 root cause analysis. 매 fairness counterfactual.
**언제 X**: 매 pure prediction (ML 의 OK). 매 LLM 의 alone (weak on step 2-3).
## ❌ 안티패턴
- **Correlation = causation**: 매 classic mistake.
- **Collider 의 control**: 매 spurious correlation 의 induce.
- **No DAG**: 매 hidden assumption.
- **Single method**: 매 sensitivity 의 X.
- **No refutation**: 매 fragile estimate.
- **Simpson's paradox 의 unaware**: 매 misleading.
- **LLM 의 causal claim 의 trust**: 매 association level 만.
## 🧪 검증 / 중복
- Verified (Pearl "Book of Why", Hernán "Causal Inference: What If", DoWhy paper).
- 신뢰도 A.
- Related: [[Bayesian-Statistics]] · [[Algorithmic-Fairness]] · [[Bias-Correction-Algorithm]] · [[A-B-Testing]] · [[Anthropic-Principle]].
## 🕓 Changelog
| 날짜 | 변경 |
|---|---|
| 2026-05-08 | Phase 1 |
| 2026-05-10 | Manual cleanup — Pearl ladder + DAG + 매 DoWhy / PSM / DiD / Causal Forest code |