0
0

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?

[Statistics] 検定の条件分岐マップ

Last updated at Posted at 2025-10-12

検定一覧

種類 検定統計量 分布 検定方向
平均の検定
- 母分散既知(1標本Z検定)
$\displaystyle Z=\frac{\bar{X}-\mu_0}{\sigma/\sqrt{n}}$ 標準正規分布 $N(0,1)$ 両側/片側
平均の検定
- 母分散未知(1標本t検定)
$\displaystyle t=\frac{\bar{X}-\mu_0}{s/\sqrt{n}}$ t分布(自由度$n-1$) 両側/片側
2標本平均の検定
- 母分散既知
$\displaystyle Z=\frac{\bar{X}_1-\bar{X}_2}{\sqrt{\sigma_1^2/n_1+\sigma_2^2/n_2}}$ 標準正規分布 $N(0,1)$ 両側/片側
2標本平均の検定
- 母分散未知(Welch)
$\displaystyle t=\frac{\bar{X}_1-\bar{X}_2}{\sqrt{s_1^2/n_1+s_2^2/n_2}}$ $t(\nu)$分布(Welchの自由度) 両側/片側
2標本平均の検定
- 母分散未知・等分散(Student)
$\displaystyle t=\frac{\bar{X}_1-\bar{X}_2}{s_p\sqrt{1/n_1+1/n_2}}$
ただし $\displaystyle s_p^2=\frac{(n_1-1)s_1^2+(n_2-1)s_2^2}{n_1+n_2-2}$
$t(n_1+n_2-2)$ 両側/片側
2標本平均の検定
- 等分散Student(展開形)
$\displaystyle t=\frac{\bar{X}_1-\bar{X}_2}{\sqrt{\left(\frac{1}{n_1}+\frac{1}{n_2}\right)\frac{\sum(X_1i-\bar{X}_1)^2+\sum({X}_2i-\bar{X}_2)^2}{n_1+n_2-2}}}$ $t(n_1+n_2-2)$ 両側/片側
比率の検定(1標本Z検定) $\displaystyle Z=\frac{\hat{p}-p_0}{\sqrt{p_0(1-p_0)/n}}$ 標準正規分布 $N(0,1)$ 両側/片側
2標本比率のZ検定 $\displaystyle Z=\frac{\hat{p}_1-\hat{p}_2}{\sqrt{\hat{p}_1(1-\hat{p}_1)/n_1+\hat{p}_2(1-\hat{p}_2)/n_2}}$ 標準正規分布 $N(0,1)$ 両側/片側
分散の検定
- 等分散性(2標本F検定)
$\displaystyle F=\frac{s_1^2}{s_2^2}$ F分布 $F(n_1-1, n_2-1)$ 右片側(両側も可)
適合度の検定 $\displaystyle \chi^2 = \sum \frac{(O_i - E_i)^2}{E_i}$ $\chi^2(k-1-c)$ 右片側
独立性の検定 $\displaystyle \chi^2 = \sum \frac{(O_{ij} - E_{ij})^2}{E_{ij}}$ $\chi^2((r-1)(c-1))$ 右片側
同等性の検定 $\displaystyle \chi^2 = \sum \frac{(O_{ij} - E_{ij})^2}{E_{ij}}$ $\chi^2((r-1)(c-1))$ 右片側
0
0
0

Register as a new user and use Qiita more conveniently

  1. You get articles that match your needs
  2. You can efficiently read back useful information
  3. You can use dark theme
What you can do with signing up
0
0

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?