Graphique d'estimation

import matplotlib.pyplot as plt
import numpy as np
import seaborn as sns
import statsmodels.api as sm
from scipy import stats

# Data: violent crimes per 100,000 residents in 2009, by state poverty rate
df = sm.datasets.statecrime.load_pandas().data
cut = df.poverty.median()
df["group"] = np.where(df.poverty > cut, "High poverty", "Low poverty")
low = df.loc[df.group == "Low poverty", "violent"].to_numpy()
high = df.loc[df.group == "High poverty", "violent"].to_numpy()

# Mean difference with a BCa bootstrap 95% CI, and the bootstrap distribution
diff = lambda a, b, axis=-1: np.mean(b, axis=axis) - np.mean(a, axis=axis)
boot = stats.bootstrap((low, high), diff, n_resamples=5000, method="BCa",
                       random_state=np.random.default_rng(1))
lo, hi = boot.confidence_interval
delta = high.mean() - low.mean()
t = stats.ttest_ind(high, low, equal_var=False)

# Manual layout (the long subtitle would otherwise squeeze the panels apart)
fig, (ax, ax2) = plt.subplots(1, 2, figsize=(8, 5.2), width_ratios=[2.2, 1], layout="none")
fig.subplots_adjust(wspace=0.12)
palette = ["#8E8E93", "#007AFF"]
sns.swarmplot(data=df, x="group", y="violent", hue="group", palette=palette, size=5,
              order=["Low poverty", "High poverty"], hue_order=["Low poverty", "High poverty"],
              legend=False, ax=ax)
for i, d in enumerate([low, high]):            # mean ± SD as a gapped line beside the swarm
    m, s = d.mean(), d.std(ddof=1)
    ax.vlines(i + 0.32, m - s, m + s, color="#3A3A3C", lw=1.5)
    ax.scatter(i + 0.32, m, s=30, color="white", edgecolor="#3A3A3C", lw=1.5, zorder=3)
ax.set_xlabel("")
ax.set_ylabel("Violent crimes per 100,000 residents")
ax.set_xticks([0, 1], [f"Poverty ≤ {cut:.1f}%\n(n = {len(low)} states)",
                      f"Poverty > {cut:.1f}%\n(n = {len(high)} states)"])

# Floating difference axis: zero aligned with the low-poverty mean
ax.set_xlim(-0.55, 1.6)
ymin, ymax = ax.get_ylim()
ax2.set_ylim(ymin - low.mean(), ymax - low.mean())
ax2.axhline(0, color="#3A3A3C", lw=1)
ax2.axhline(delta, color="#3A3A3C", lw=1, ls=":")
ax.plot([0.32, 1.6], [low.mean()] * 2, color="#3A3A3C", lw=0.8)
ax.plot([1.32, 1.6], [high.mean()] * 2, color="#3A3A3C", lw=0.8, ls=":")
v = ax2.violinplot(boot.bootstrap_distribution, positions=[0], widths=0.8,
                   showextrema=False, side="high")
v["bodies"][0].set(facecolor="#007AFF", alpha=0.3, edgecolor="none")
ax2.vlines(0, lo, hi, color="#1D1D1F", lw=2.5)
ax2.scatter(0, delta, s=70, color="#1D1D1F", zorder=3)
ax2.annotate(f"Δ = {delta:+.0f}\n[{lo:.0f}, {hi:.0f}]", (0, hi), xytext=(-6, 8),
             textcoords="offset points", ha="right", va="bottom", fontsize=9.5,
             fontweight="semibold", color="#007AFF")
ax2.set_xlim(-0.6, 0.6)
ax2.set_xticks([0], ["High − Low"])
ax2.yaxis.tick_right(); ax2.yaxis.set_label_position("right")
ax2.spines[["left"]].set_visible(False); ax2.spines["right"].set_visible(True)
ax2.set_ylabel("Mean difference (crimes per 100,000)")
ax2.grid(False)

ax.set_title(f"High-poverty states record {delta:.0f} more violent crimes per 100,000 on average",
             pad=26)
ax.text(0, 1.02, f"BCa bootstrap 95% CI [{lo:.0f}, {hi:.0f}] (5,000 resamples) · "
        f"Welch's t({t.df:.1f}) = {t.statistic:.2f}, p = {t.pvalue:.3f} · 2009 data",
        transform=ax.transAxes, fontsize=9.5, color="#6E6E73")
plt.show()