베타분포 (Beta Distribution)
정의
표기
$$ X \sim Be(\alpha , \beta)$$
- $$ \alpha \in ( \ 0 \ , \ \infty \ ) $$
- $$ \beta \in ( \ 0 \ , \ \infty \ ) $$
받침
$$ x \in [ \ 0 \ , \ 1 \ ] $$
확률밀도함수
$$f(x)= \left[ \frac{\Gamma(\alpha+\beta)}{\Gamma(\alpha)\Gamma(\beta)} \right] x^{a-1}(1-x)^{\beta-1} $$
(1) 그래프 : $\alpha \ \mathrm{or} \ \beta \ = \ 1$
(2) 그래프 : $\alpha \ = \ \beta \ < \ 1$
(3) 그래프 : $\alpha \ = \ \beta > 1$
(4) 그래프 : $1 \ < \ \alpha \ < \ \beta \ \mathrm{or} \ 1 \ < \ \beta \ < \ \alpha$
누적분포함수
$$ F(x) = I( \ x \ ; \ \alpha \ , \ \beta \ ) $$
- 단, $I( \ x \ ; \ \alpha \ , \ \beta \ )$는 정칙 베타함수이다.
(1) 그래프 : $\alpha \ \mathrm{or} \ \beta \ = \ 1$
(2) 그래프 : $\alpha \ = \ \beta \ < \ 1$
(3) 그래프 : $\alpha \ = \ \beta > 1$
(4) 그래프 : $1 \ < \ \alpha \ < \ \beta \ \mathrm{or} \ 1 \ < \ \beta \ < \ \alpha$
기대값
$$E(X)=\frac{\alpha}{\alpha+\beta}$$
분산
$$Var(X)=\frac{\alpha\beta}{(\alpha+\beta)^{2}(\alpha+\beta+1)}$$
왜도
$$ \gamma_{1} = \frac{2(\beta - \alpha) \sqrt{1 + \alpha + \beta}}{\sqrt{\alpha \beta} (2 + \alpha + \beta)} $$
첨도
$$ \gamma_{2} = \frac{6 \left[ \alpha^{3} + \alpha^{2} (1 - 2 \beta) + \beta^{2} (1 + \beta) - 2 \alpha \beta (2 + \beta) \right] }{\alpha \beta (\alpha + \beta + 2) (\alpha + \beta + 3)} $$
특성함수
$$ \phi \ (t) = \ _{1}F_{1} (\alpha \ ; \ \alpha + \beta \ ; \ i \cdot t) $$
원적률
$$ \mu'_{k} = \frac{\Gamma (\alpha + \beta) \cdot \Gamma (\alpha + k)}{\Gamma (\alpha + \beta + k) \cdot \Gamma (\alpha)} $$