Question

我使用scipy库进行了t检验分析，并想与自己制作的t检验函数进行交叉检查。令我惊讶的是，当我的系列不包含任何Nan值时，我的函数和scipy库给出了相同的t值和p值。如果该系列具有任何nan值，尽管我已删除了nan值，但仍存在一些差异。有谁知道可能导致此问题的问题？

from math import sqrt
from numpy import mean
from scipy.stats import t
import numpy as np
import pandas as pd
from scipy import stats

# function for calculating the t-test for two independent samples
def independent_ttest(data1, data2, alpha):
    # calculate means
    mean1, mean2 = mean(data1), mean(data2)
    # calculate standard errors
    se1, se2 = sem(data1), sem(data2)
    # standard error on the difference between the samples
    sed = sqrt(se1**2.0 + se2**2.0)
    # calculate the t statistic
    t_stat = (mean1 - mean2) / sed

    # degrees of freedom
    df = len(data1) + len(data2) - 2
    # calculate the critical value
    cv = t.ppf(1.0 - alpha, df)
    # calculate the p-value
    p = (1.0 - t.cdf(abs(t_stat), df)) * 2.0
    # return everything

    return t_stat, df, cv, p

# calculate the t test
alpha = 0.05
x = np.arange(10.)
b = x*1.1
df_x = pd.Series(x)
df_b = pd.Series(b)
df_x_nan = df_x.replace(7.0, np.nan)
df_x_nan = df_x.replace(4.0, np.nan)

print('Whithout NaN')
t_stat, df, cv, p = independent_ttest(df_x, df_b, alpha)
t_stat_scipy, p_scipy = stats.ttest_ind(df_x,df_b, nan_policy = 'omit')
print("t-test function, t_Stat: {}".format(t_stat))
print("t-test scipy, t_Stat: {}".format(t_stat_scipy))
print("t-test function, p: {}".format(p))
print("t-test scipy, p: {}".format(p_scipy))
print('===================')
print('Whith NaN')
t_stat, df, cv, p = independent_ttest(df_x_nan.dropna(), df_b, alpha)
t_stat_scipy, p_scipy = stats.ttest_ind(df_x_nan,df_b, nan_policy = 'omit')
print("t-test function, t_Stat: {}".format(t_stat))
print("t-test scipy, t_Stat: {}".format(t_stat_scipy))
print("t-test function,p: {}".format(p))
print("t-test scipy, p: {}".format(p_scipy))

以下是输出：

Whithout NaN
t-test function, t_Stat: -0.3161627186509306
t-test scipy, t_Stat: -0.31616271865093054
t-test function, p: 0.7555158566691087
t-test scipy, p: 0.7555158566691088
===================
Whith NaN
t-test function, t_Stat: -0.2628962556410858
t-test scipy, t_Stat: -0.2623389223791333
t-test function,p: 0.7957901706958825
t-test scipy, p: 0.7962126903526476

有/没有nan值的t检验与我自己的t检验函数

0 个答案: