The Third T-Test

              
1234567891011121314151617181920
            
# Import libraries
import pandas as pd
from scipy.stats import levene

# Read .csv files
df_control = pd.read_csv('https://codefinity-content-media.s3.eu-west-1.amazonaws.com/c3b98ad3-420d-403f-908d-6ab8facc3e28/ab_control.csv', delimiter=';')
df_test = pd.read_csv('https://codefinity-content-media.s3.eu-west-1.amazonaws.com/c3b98ad3-420d-403f-908d-6ab8facc3e28/ab_test.csv', delimiter=';')

# Do Levene's test 
statistic, p_value = levene(df_control['Purchase'], df_test['Purchase'])

# Print result of Levene's test
print('Statistic:', statistic)
print('p-value:', p_value)

# Determine whether the variances are similar
if p_value > 0.05:
  print('The variances of the two groups are NOT statistically different')
else:
  print('The variances of the two groups are statistically different')

              
123456789101112131415161718
            
# Import libraries
import pandas as pd
from scipy.stats import ttest_ind

# Read .csv files
df_control = pd.read_csv('https://codefinity-content-media.s3.eu-west-1.amazonaws.com/c3b98ad3-420d-403f-908d-6ab8facc3e28/ab_control.csv', delimiter=';')
df_test = pd.read_csv('https://codefinity-content-media.s3.eu-west-1.amazonaws.com/c3b98ad3-420d-403f-908d-6ab8facc3e28/ab_test.csv', delimiter=';')

# Select only the 'Purchase' columns
data_control = df_control['Purchase']
data_test = df_test['Purchase']

# Do T-Test 
statistic, p_value = ttest_ind(data_control, data_test, equal_var=True)

# Print result of T-test
print('Statistic:', statistic)
print('p-value:', p_value)