Editing Causal Inference in AI (section)

== <span style="color: #FFFFFF;">Applying</span> ==
'''Estimating causal treatment effects with DoWhy:'''

<syntaxhighlight lang="python">
import dowhy
from dowhy import CausalModel
import pandas as pd
import numpy as np

# Generate synthetic data: drug → recovery, age → both drug and recovery (confounder)
np.random.seed(42)
n = 1000
age = np.random.normal(50, 15, n)
drug = (0.3 * age + np.random.normal(0, 10, n) > 30).astype(int)  # older → more likely to receive drug
recovery = 0.5 * drug - 0.02 * age + np.random.normal(0, 1, n)   # drug helps, but age hurts

df = pd.DataFrame({'age': age, 'drug': drug, 'recovery': recovery})

# Step 1: Define the causal model as a DAG
model = CausalModel(
    data=df,
    treatment="drug",
    outcome="recovery",
    common_causes=["age"]  # age is a confounder
)

# Step 2: Identify the causal effect
identified_estimand = model.identify_effect(proceed_when_unidentifiable=True)
print(identified_estimand)

# Step 3: Estimate the causal effect (controlling for age via backdoor adjustment)
estimate = model.estimate_effect(
    identified_estimand,
    method_name="backdoor.linear_regression",
    control_value=0,
    treatment_value=1,
)
print(f"Estimated ATE: {estimate.value:.3f}")
# Should recover ~0.5 (the true causal effect)

# Naive regression ignoring confounding:
naive_corr = df[df.drug==1]['recovery'].mean() - df[df.drug==0]['recovery'].mean()
print(f"Naive (biased) correlation: {naive_corr:.3f}")
# Will be biased because older people receive drug more but recover less

# Step 4: Refute the estimate (robustness checks)
refutation = model.refute_estimate(estimate,
                                   method_name="random_common_cause")
print(refutation)  # Good estimate: adding random confounder shouldn't change result
</syntaxhighlight>

; Causal inference methods by scenario
: '''RCT available''' → Compute difference in means (no adjustment needed — randomization handles confounding)
: '''Observational, confounders known''' → Propensity score matching, IPW, doubly-robust estimators
: '''Observational, confounders unknown''' → Instrumental variables (IV), regression discontinuity
: '''Time series, sequential treatments''' → G-computation, marginal structural models
: '''Causal structure unknown''' → Causal discovery: PC algorithm, FCI, LiNGAM, NOTEARS
: '''Heterogeneous effects''' → Causal forests, meta-learners (S, T, X-learner)
</div>

<div style="background-color: #8B4500; color: #FFFFFF; padding: 20px; border-radius: 8px; margin-bottom: 15px;">