Try It Difference of Means


                    ## The data:
                    import pandas as pd
                    import numpy as np
                    df = pd.DataFrame({'Mileage' : ['Low']*5 + ['High']*12,
                                       'Range' : [240, 241, 236, 240, 240, 230, 227, 232, 
                                                  255.4381603, 267.2467371, 225, 238,
                                                  223, 225, 218, 227, 225]})
                    
                    ## STEP 1: Calculate the sample statistic
                    
                    
                    ## STEP 2: Randomization distribution
                    
                    
                    ## STEP 3: Calculate p-value. Direction of inequality agrees with Ha above!!!


                    ## The data:
                    import pandas as pd
                    import numpy as np
                    df = pd.DataFrame({'Mileage' : ['Low']*5 + ['High']*12,
                                       'Range' : [240, 241, 236, 240, 240, 230, 227, 232, 
                                                  255.4381603, 267.2467371, 225, 238,
                                                  223, 225, 218, 227, 225]})
                    
                    ## STEP 1: Calculate the sample statistic
                    means = df.groupby('Mileage').mean()
                    sampdiff = means.loc['Low', 'Range'] - means.loc['High', 'Range']
                    print("Low Mileage Mean = ", means.loc['Low', 'Range'])
                    print("High Mileage Mean = ", means.loc['High', 'Range'])
                    print("Sample difference of means = ", sampdiff)
                    
                    ## STEP 2: Randomization distribution
                    sim = df.copy(deep = True)
                    N = 1000
                    n = sim.shape[0]  # num. rows
                    xbardiff = np.empty(N)
                    for i in range(N):
                      sim['Range'] = np.random.choice(sim['Range'], size=n, replace=False)
                      means = sim.groupby('Mileage').mean()
                      xbardiff[i] = means.loc['Low', 'Range'] - means.loc['High', 'Range']
                    
                    ## STEP 3: Calculate p-value. Direction of inequality agrees with Ha above!!!
                    print("p-value =", len(xbardiff[xbardiff >= sampdiff])/N)