正态分布下含绝对值的期望求解
首先用伽马函数来证明一个小结论。
设 X ∼ N ( 0 , 1 ) , 求 E ∣ X ∣ X\sim N(0,1),求E|X| X∼N(0,1),求E∣X∣
分析:我们知道EX=0,那是因为根据表达式:
f ( x ) = 1 2 π σ e − ( x − μ ) 2 2 σ 2 = 1 2 π e − x 2 2 f(x) = \frac{1}{\sqrt {2\pi}\sigma}e^{-\frac{(x-\mu)^2}{2\sigma^2}} = \frac{1}{\sqrt {2\pi}}e^{-\frac{x^2}{2}} f(x)=2πσ1e−2σ2(x−μ)2=2π1e−2x2
E X = ∫ − ∞ + ∞ x f ( x ) d x = 0 EX = \int_{-\infty}^{+\infty}xf(x)dx = 0 EX=∫−∞+∞xf(x)dx=0
而
E ∣ X ∣ = ∫ − ∞ + ∞ x 2 f ( x ) d x = ∫ − ∞ + ∞ ∣ x ∣ 1 2 π e − x 2 2 d x = 2 ∫ − ∞ + ∞ ∣ x 2 ∣ 1 2 π e − ( x 2 ) 2 d ( x 2 ) = 2 1 2 π ⋅ 2 ∫ 0 + ∞ x 2 e − ( x 2 ) 2 d ( x 2 ) = 2 1 2 π Γ ( 1 ) = 2 π E|X| = \int_{-\infty}^{+\infty}x^2f(x)dx \\ = \int_{-\infty}^{+\infty}|x| \frac{1}{\sqrt {2\pi}}e^{-\frac{x^2}{2}}dx \\ = 2\int_{-\infty}^{+\infty}|\frac{x}{\sqrt 2}| \frac{1}{\sqrt {2\pi}}e^{-(\frac{x}{\sqrt 2})^2}d(\frac{x}{\sqrt 2})\\ = 2 \frac{1}{\sqrt {2\pi}}\cdot 2\int_0^{+\infty}\frac{x}{\sqrt 2}e^{-(\frac{x}{\sqrt 2})^2}d(\frac{x}{\sqrt 2})\\ = 2 \frac{1}{\sqrt {2\pi}}\Gamma(1) =\sqrt {\frac{2}{\pi}} E∣X∣=∫−∞+∞x2f(x)dx=∫−∞+∞∣x∣2π1e−2x2dx=2∫−∞+∞∣2x∣2π