FAANG 데이터 사이언스 인터뷰에서 가장 흔한 5가지 통계적 함정

import pandas as pd

data = pd.DataFrame({
    'device': ['mobile', 'mobile', 'desktop', 'desktop'],
    'variant': ['A', 'B', 'A', 'B'],
    'converts': [40, 765, 90, 10],
    'visitors': [100, 900, 900, 100],
})
data['rate'] = data['converts'] / data['visitors']

print('Per device:')
print(data[['device', 'variant', 'rate']].to_string(index=False))

print('
Aggregate (misleading):')
agg = data.groupby('variant')[['converts', 'visitors']].sum()
agg['rate'] = agg['converts'] / agg['visitors']
print(agg['rate'])

import numpy as np

np.random.seed(42)
satisfaction = np.random.choice([0, 1], size=1000, p=[0.5, 0.5])
response_prob = np.where(satisfaction == 1, 0.8, 0.2)
responded = np.random.rand(1000) < response_prob

print(f"True satisfaction rate: {satisfaction.mean():.2%}")
print(f"Survey satisfaction rate: {satisfaction[responded].mean():.2%}")

from scipy import stats

n_tests, alpha = 20, 0.05
false_positives = 0
for _ in range(n_tests):
    a = np.random.normal(0, 1, 1000)
    b = np.random.normal(0, 1, 1000)
    if stats.ttest_ind(a, b).pvalue < alpha:
        false_positives += 1

print(f'Tests run: {n_tests}')
print(f'False positives (p<0.05): {false_positives}')