blob: 3ebba8412122aa32d874d00dabec84337269af12 (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
|
## Import the packages
import numpy as np
from scipy import stats
## Define 2 random distributions
#Sample Size
N = 10
#Gaussian distributed data with mean = 2 and var = 1
a = np.random.randn(N) + 2
#Gaussian distributed data with with mean = 0 and var = 1
b = np.random.randn(N)
## Calculate the Standard Deviation
#Calculate the variance to get the standard deviation
#For unbiased max likelihood estimate we have to divide the var by N-1, and therefore the parameter ddof = 1
var_a = a.var(ddof=1)
var_b = b.var(ddof=1)
#std deviation
s = np.sqrt((var_a + var_b)/2)
print(a)
print(b)
## Calculate the t-statistics
t = (a.mean() - b.mean())/(s*np.sqrt(2/N))
## Compare with the critical t-value
#Degrees of freedom
df = 2*N - 2
#p-value after comparison with the t
p = 1 - stats.t.cdf(t,df=df)
print("t = " + str(t))
print("p = " + str(2*p)) # 双尾
### You can see that after comparing the t statistic with the critical t value (computed internally) we get a good p value of 0.0005 and thus we reject the null hypothesis and thus it proves that the mean of the two distributions are different and statistically significant.
## Cross Checking with the internal scipy function
t2, p2 = stats.ttest_ind(a,b)
print("t = " + str(t2))
print("p = " + str(p2))
|
