Check Covariate Balance in Python

import numpy as np
from scipy import stats

def balance_check(treatment, covariate):
    """Check covariate balance between treatment and control groups."""
    treat_vals = covariate[treatment == 1]
    control_vals = covariate[treatment == 0]
    
    # Standardized mean difference
    pooled_std = np.sqrt((np.var(treat_vals) + np.var(control_vals)) / 2)
    smd = (np.mean(treat_vals) - np.mean(control_vals)) / pooled_std if pooled_std > 0 else 0
    
    # Kolmogorov-Smirnov test for distribution similarity
    ks_stat, ks_pval = stats.ks_2samp(treat_vals, control_vals)
    
    return smd, ks_stat, ks_pval

if __name__ == "__main__":
    # Mock data: 100 subjects, 50 treated
    np.random.seed(42)
    n = 100
    treatment = np.random.binomial(1, 0.5, n)
    age = np.random.normal(45, 10, n)
    income = np.random.normal(50000, 15000, n)
    
    var_smd, ks_stat, ks_pval = balance_check(treatment, age)
    print(f"Age balance -> SMD: {var_smd:.3f}, KS stat: {ks_stat:.3f}, p-value: {ks_pval:.3f}")
    
    var_smd, ks_stat, ks_pval = balance_check(treatment, income)
    print(f"Income balance -> SMD: {var_smd:.3f}, KS stat: {ks_stat:.3f}, p-value: {ks_pval:.3f}")