Axes = plt.subplots (2, 2, figsize=(14.10, 10)).
colors_a = ["gray", "#1f77b4", "#ff7f0e", "#2ca02c", "#d62728"][: len(asmd_means)]
Axes[0, 0].bar(list(asmd_means.keys()), list(asmd_means.values()), color=colors_a)
Axes[0, 0].axhline(0.1, ls="--", color="red", label="0.10 imbalance threshold")
Axes[0, 0].set_title("Mean ASMD across covariates")
Axes[0, 0].set_ylabel("Mean ASMD"The axes[0, 0].legend()
Axes[0, 0].tick_params(axis="x", rotation=20)
Truth = target_df["happiness"].mean()
colors_b = ["#888"] + ["#1f77b4", "#ff7f0e", "#2ca02c", "#d62728"][: len(methods)] + ["black"]
Axes[0, 1].bar(list(outcome_means.keys()), list(outcome_means.values()),
color=colors_b[: len(outcome_means)])
Axes[0, 1].axhline(truth, ls="--", color="black", label=f"truth = {truth:.2f}")
Axes[0, 1].set_title("Estimated mean happiness vs ground truth")
Axes[0, 1].set_ylabel("Mean happiness"The axes[0, 1].legend()
Axes[0, 1].tick_params(axis="x", rotation=20)
w_ipw = adjusted_ipw.to_df()["weight"].values
Axes[1, 0].hist(w_ipw, bins=40, color="steelblue", edgecolor="white")
Axes[1, 0].set_title(
F"IPW weight distributionn"
The f"min={w_ipw.min():.2f} median={np.median(w_ipw):.2f} max={w_ipw.max():.2f}"
)
Axes[1, 0].set_xlabel("weight"( ) axes[1, 0].set_ylabel("count")
Sample_df = ages["age"].values
Bins = np.linspace (18, 90, 31,
Axes[1, 1].hist(target_df["age"], bins=bins, density=True, alpha=0.45,
color="green", label="Target (truth)")
Axes[1, 1].hist(ages, bins=bins, density=True, alpha=0.45,
color="red", label="Sample (biased)")
Axes[1, 1].hist(ages, bins=bins, density=True, alpha=0.45,
color="blue", weights=w_ipw, label="Sample (IPW-weighted)")
Axes[1, 1].set_title("Age distribution: bias correction by IPW")
Axes[1, 1].set_xlabel("Age"( ) axes[1, 1].set_ylabel("density"( ) axes[1, 1].legend()
plt.tight_layout()
plt.savefig("balance_diagnostics.png", dpi=110, bbox_inches="tight")
plt.show()
print("n" + "=" * 60)
print(" ADVANCED — controlling variance with max_de")
print("=" * 60)
print("max_de=1.5 trims extreme weights so the design effect stays ≤ 1.5,")
print("trading a little bias for tighter confidence intervals.n")
adjusted_trim = sample_with_target.adjust(method="ipw", max_de=1.5)
print(adjusted_trim.summary())
Out = adjusted_ipw.to_df()
out.to_csv("balance_weighted_sample.csv", index=False)
print("nSaved weighted sample → balance_weighted_sample.csv")
print("Saved diagnostics plot → balance_diagnostics.png")
print("nFirst 5 rows of weighted output:")
print(out.head())
err_naive = abs(sample_df["happiness"].mean() - truth)
err_ipw = abs(outcome_means["IPW"] - truth)
print("n" + "=" * 60)
print(" BIAS REDUCTION SUMMARY")
print("=" * 60)
print(f"Naive estimator error : {err_naive:.3f}")
print(f"IPW estimator error : {err_ipw:.3f}")
print(f"Bias reduction : {(1 - err_ipw / max(err_naive, 1e-9)) * 100:.1f}%")
Trending
- OpenRouter Cuts Three Suppliers After AI Immediate Publicity Findings – Unite.AI
- A Group of Researchers from Columbia and CertiK Introduce TensorLean for Formal Verification of GPU Kernels
- Collectively AI Discloses Immediate Leak After Coding Agent Uncovered Credential – Unite.AI
- Dragos Finds Immediate Leaks and Stolen Keys in AI Provide Chains
- Lean and Mathlib Communities Certify Claude-Assisted Riemann Proof – Unite.AI
- AWS Routes HyperPod Inference Throughout Areas From One Endpoint – Unite.AI
- DailyAI Briefing: A Lean-checked Riemann proof, plus 4 extra
- Anthropic Shares Drop 8.5% in Second Session Throughout AI Selloff – Unite.AI

