def pearson_r(x, y):
assert len(x) == len(y)
x_bar = average(x)
y_bar = average(y)
s_x = sqrt(s_2(x))
s_y = sqrt(s_2(y))
tmp = 0.0
for i in range(0, len(x)):
tmp += ((x[i] - x_bar) * (y[i] - y_bar) / s_x / s_y)
return tmp / (len(x) - 1)
def infer_by_chi(l1, l2, alpha=0.01):
ss1 = s_2(l1)
ss2 = s_2(l2)
fv = ss1 / ss2
from scipy.stats import f
res = f.ppf(1 - alpha, len(l1) - 1, len(l2) - 1)
print('res {} fv {}'.format(res, fv))
if res > fv:
print('sigma1 <= sigma2')
else:
print('sigma1 > sigma2')
def infer_by_chi(l1, l2, alpha=0.01):
ss1 = s_2(l1)
ss2 = s_2(l2)
fv = ss1 / ss2
from scipy.stats import f
res = f.ppf(1 - alpha, len(l1) - 1, len(l2) - 1)
print('res {} fv {}'.format(res, fv))
if res > fv:
print('sigma1 <= sigma2')
else:
print('sigma1 > sigma2')
def infer_by_t(l1, l2, alpha=0.01, sigma=0):
n1 = len(l1)
n2 = len(l2)
x_aver = average(l1)
y_aver = average(l2)
s_1sq = s_2(l1)
s_2sq = s_2(l2)
s_w2 = ((n1 - 1) * s_1sq + (n2 - 1) * s_2sq) / (n1 + n2 - 2)
tv = ((x_aver - y_aver) - sigma) / sqrt(s_w2 * (1 / n1 + 1 / n2))
t_a = t.ppf(alpha, n1 + n2 - 2)
print('tv {} t_a {}'.format(tv, t_a))
if tv < t_a:
print('mu1 < mu2')
else:
print('mu1 >= mu2')
def infer_by_t(l1, l2, alpha=0.01, sigma=0):
n1 = len(l1)
n2 = len(l2)
x_aver = average(l1)
y_aver = average(l2)
s_1sq = s_2(l1)
s_2sq = s_2(l2)
s_w2 = ((n1 - 1) * s_1sq + (n2 - 1) * s_2sq) / (n1 + n2 - 2)
tv = ((x_aver - y_aver) - sigma) / sqrt(s_w2 * (1 / n1 + 1 / n2))
t_a = t.ppf(alpha, n1 + n2 - 2)
print('tv {} t_a {}'.format(tv, t_a))
if tv < t_a:
print('mu1 < mu2')
else:
print('mu1 >= mu2')
def t_check(l, mu, alpha=0.05):
aver = average(l)
n = len(l)
ss = s_2(l)
tt = (aver - mu) * sqrt(n) / sqrt(ss)
l, r = t.interval(1 - alpha, n - 1)
if tt > r or tt < l:
print('reject')
else:
print('accept')
import numpy as np
from numpy import var, std
from scipy.stats import stats
from statistic.check.util import s_2, sigma_2
__author__ = 'zzt'
if __name__ == '__main__':
l = [420, 500, 920, 1380, 1510, 1650, 1760, 2100, 2300, 2350]
print(stats.kstest(l, 'expon', [1500.0]))
x = np.linspace(-15, 15, 9)
print(std(x)**2)
print(var(x))
print(s_2(x))
print(sigma_2(x))
print(stats.kstest(x, 'norm', [0, 9]))