def test_weightstats_3(self):
x1_2d, x2_2d = self.x1_2d, self.x2_2d
w1, w2 = self.w1, self.w2
d1w_2d = DescrStatsW(x1_2d, weights=w1)
d2w_2d = DescrStatsW(x2_2d, weights=w2)
x1r_2d = d1w_2d.asrepeats()
x2r_2d = d2w_2d.asrepeats()
assert_almost_equal(x2r_2d.mean(0), d2w_2d.mean, 14)
assert_almost_equal(x2r_2d.var(0), d2w_2d.var, 14)
assert_almost_equal(x2r_2d.std(0), d2w_2d.std, 14)
assert_almost_equal(np.cov(x2r_2d.T, bias=1), d2w_2d.cov, 14)
assert_almost_equal(np.corrcoef(x2r_2d.T), d2w_2d.corrcoef, 14)
# print d1w_2d.ttest_mean(3)
# #scipy.stats.ttest is also vectorized
# print stats.ttest_1samp(x1r_2d, 3)
t, p, d = d1w_2d.ttest_mean(3)
assert_almost_equal([t, p], stats.ttest_1samp(x1r_2d, 3), 11)
#print [stats.ttest_1samp(xi, 3) for xi in x1r_2d.T]
cm = CompareMeans(d1w_2d, d2w_2d)
ressm = cm.ttest_ind()
resss = stats.ttest_ind(x1r_2d, x2r_2d)
assert_almost_equal(ressm[:2], resss, 14)
def test_weightstats_3(self):
x1_2d, x2_2d = self.x1_2d, self.x2_2d
w1, w2 = self.w1, self.w2
d1w_2d = DescrStatsW(x1_2d, weights=w1)
d2w_2d = DescrStatsW(x2_2d, weights=w2)
x1r_2d = d1w_2d.asrepeats()
x2r_2d = d2w_2d.asrepeats()
assert_almost_equal(x2r_2d.mean(0), d2w_2d.mean, 14)
assert_almost_equal(x2r_2d.var(0), d2w_2d.var, 14)
assert_almost_equal(x2r_2d.std(0), d2w_2d.std, 14)
assert_almost_equal(np.cov(x2r_2d.T, bias=1), d2w_2d.cov, 14)
assert_almost_equal(np.corrcoef(x2r_2d.T), d2w_2d.corrcoef, 14)
# print d1w_2d.ttest_mean(3)
# #scipy.stats.ttest is also vectorized
# print stats.ttest_1samp(x1r_2d, 3)
t, p, d = d1w_2d.ttest_mean(3)
assert_almost_equal([t, p], stats.ttest_1samp(x1r_2d, 3), 11)
# print [stats.ttest_1samp(xi, 3) for xi in x1r_2d.T]
cm = CompareMeans(d1w_2d, d2w_2d)
ressm = cm.ttest_ind()
resss = stats.ttest_ind(x1r_2d, x2r_2d)
assert_almost_equal(ressm[:2], resss, 14)
def test_ttest_2sample(self):
x1, x2 = self.x1, self.x2
x1r, x2r = self.x1r, self.x2r
w1, w2 = self.w1, self.w2
#Note: stats.ttest_ind handles 2d/nd arguments
res_sp = stats.ttest_ind(x1r, x2r)
assert_almost_equal(ttest_ind(x1, x2, weights=(w1, w2))[:2],
res_sp, 14)
#check correct ttest independent of user ddof
cm = CompareMeans(DescrStatsW(x1, weights=w1, ddof=0),
DescrStatsW(x2, weights=w2, ddof=1))
assert_almost_equal(cm.ttest_ind()[:2], res_sp, 14)
cm = CompareMeans(DescrStatsW(x1, weights=w1, ddof=1),
DescrStatsW(x2, weights=w2, ddof=2))
assert_almost_equal(cm.ttest_ind()[:2], res_sp, 14)
cm0 = CompareMeans(DescrStatsW(x1, weights=w1, ddof=0),
DescrStatsW(x2, weights=w2, ddof=0))
cm1 = CompareMeans(DescrStatsW(x1, weights=w1, ddof=0),
DescrStatsW(x2, weights=w2, ddof=1))
cm2 = CompareMeans(DescrStatsW(x1, weights=w1, ddof=1),
DescrStatsW(x2, weights=w2, ddof=2))
res0 = cm0.ttest_ind(usevar='unequal')
res1 = cm1.ttest_ind(usevar='unequal')
res2 = cm2.ttest_ind(usevar='unequal')
assert_almost_equal(res1, res0, 14)
assert_almost_equal(res2, res0, 14)
#check confint independent of user ddof
res0 = cm0.tconfint_diff(usevar='pooled')
res1 = cm1.tconfint_diff(usevar='pooled')
res2 = cm2.tconfint_diff(usevar='pooled')
assert_almost_equal(res1, res0, 14)
assert_almost_equal(res2, res0, 14)
res0 = cm0.tconfint_diff(usevar='unequal')
res1 = cm1.tconfint_diff(usevar='unequal')
res2 = cm2.tconfint_diff(usevar='unequal')
assert_almost_equal(res1, res0, 14)
assert_almost_equal(res2, res0, 14)
def test_ttest_2sample(self):
x1, x2 = self.x1, self.x2
x1r, x2r = self.x1r, self.x2r
w1, w2 = self.w1, self.w2
#Note: stats.ttest_ind handles 2d/nd arguments
res_sp = stats.ttest_ind(x1r, x2r)
assert_almost_equal(ttest_ind(x1, x2, weights=(w1, w2))[:2],
res_sp, 14)
#check correct ttest independent of user ddof
cm = CompareMeans(DescrStatsW(x1, weights=w1, ddof=0),
DescrStatsW(x2, weights=w2, ddof=1))
assert_almost_equal(cm.ttest_ind()[:2], res_sp, 14)
cm = CompareMeans(DescrStatsW(x1, weights=w1, ddof=1),
DescrStatsW(x2, weights=w2, ddof=2))
assert_almost_equal(cm.ttest_ind()[:2], res_sp, 14)
cm0 = CompareMeans(DescrStatsW(x1, weights=w1, ddof=0),
DescrStatsW(x2, weights=w2, ddof=0))
cm1 = CompareMeans(DescrStatsW(x1, weights=w1, ddof=0),
DescrStatsW(x2, weights=w2, ddof=1))
cm2 = CompareMeans(DescrStatsW(x1, weights=w1, ddof=1),
DescrStatsW(x2, weights=w2, ddof=2))
res0 = cm0.ttest_ind(usevar='separate')
res1 = cm1.ttest_ind(usevar='separate')
res2 = cm2.ttest_ind(usevar='separate')
assert_almost_equal(res1, res0, 14)
assert_almost_equal(res2, res0, 14)
#check confint independent of user ddof
res0 = cm0.confint_diff(usevar='pooled')
res1 = cm1.confint_diff(usevar='pooled')
res2 = cm2.confint_diff(usevar='pooled')
assert_almost_equal(res1, res0, 14)
assert_almost_equal(res2, res0, 14)
res0 = cm0.confint_diff(usevar='separate')
res1 = cm1.confint_diff(usevar='separate')
res2 = cm2.confint_diff(usevar='separate')
assert_almost_equal(res1, res0, 14)
assert_almost_equal(res2, res0, 14)
a = 0.05 # 有意水準（デフォルト） = 1 - 信頼係数
alt = 'two-sided' # 両側検定（デフォルト）
# 左片側検定なら'smaller'
# 右片側検定なら'larger'
d = DescrStatsW(np.array(X) - np.array(Y)) # 対標本の場合
d.ttest_mean(alternative=alt)[1] # p値
#> 0.0006415571512322235
d.tconfint_mean(alpha=a, alternative=alt) # 信頼区間
#> (-3.9955246743198867, -1.3644753256801117)
c = CompareMeans(DescrStatsW(X), DescrStatsW(Y)) # 対標本でない場合
ve = 'pooled' # 等分散を仮定する（デフォルト）．仮定しないなら'unequal'．
c.ttest_ind(alternative=alt, usevar=ve)[1] # p値
#> 0.000978530937238609
c.tconfint_diff(alpha=a, alternative=alt, usevar=ve) # 信頼区間
#> (-4.170905570517185, -1.1890944294828283)
### 4.4.4 独立性の検定（カイ2乗検定）
import pandas as pd
my_url = ('https://raw.githubusercontent.com/taroyabuki'
'/fromzero/master/data/smoker.csv')
my_data = pd.read_csv(my_url)
my_data.head()
#> alive smoker
#> 0 Yes No
