高斯K阶矩计算

---

一、计算$E(x^k)$

高斯概率密度函数（PDF）为
$$f(x)=\frac{1}{\sqrt{2\pi }\sigma }\exp \left(-\frac{(x-\mu {)}^2}{2{\sigma }^2}\right)$$

$E(x^k)$为$X$的$k$阶中心矩，
$$\begin{array}{rl}E\left(X^k\right)& ={\int }_{-\infty }^{\infty }{x}^{k}f(x)\mathrm{d}x\\ & =\frac{1}{\sqrt{2\pi }\sigma }{\int }_{-\infty }^{\infty }{x}^k\exp \left(-\frac{(x-\mu {)}^2}{2{\sigma }^2}\right)\mathrm{d}x\end{array}$$
当$\mu =0$时，
$$\begin{array}{rl}E\left(X^k\right)& =\frac{1}{\sqrt{2\pi }\sigma }{\int }_{-\infty }^{\infty }{x}^k\exp \left(-\frac{x^2}{2{\sigma }^2}\right)\mathrm{d}x\\ & =\frac{{\sigma }^k}{\sqrt{2\pi }\sigma }\cdot {\int }_{-\infty }^{+\infty }{\left(\frac{x}{\sigma }\right)}^k\cdot \exp \left(-\frac{1}{2}{\left(\frac{x}{\sigma }\right)}^2\right)dx\\ & =\frac{{\sigma }^k}{\sqrt{2\pi }}{\int }_{-\infty }^{+\infty }{u}^k\exp \left(-\frac{u^2}{2}\right)du\end{array}$$

1. $k=奇数$ 时，$E\left(X^k\right)=0$
2. $k=偶数$ 时，$$\begin{array}{rl}E\left(X^k\right)& =\sqrt{\frac{2}{\pi }}{\sigma }^k{\int }_0^{+\infty }{u}^k\exp \left(-\frac{u^2}{2}\right)du\\ & =\sqrt{\frac{2}{\pi }}{\sigma }^k{\int }_0^{+\infty }(\sqrt{2x}{)}^{k-1}{e}^{-x}dx\\ & =\frac{(\sqrt{2}{)}^k}{\sqrt{\pi }}{\sigma }^k{\int }_0^{+\infty }{x}^{\left(\frac{k+1}{2}-1\right)}{e}^{-x}dx\\ & =\frac{(\sqrt{2}\sigma {)}^k}{\sqrt{\pi }}\Gamma \left(\frac{k+1}{2}\right)\\ & =1\cdot 3\cdot 5\cdots (k-1){\sigma }^k\end{array}$$

当$\mu \ne 0$时，（不会算）

$$E\left[(x+\mu {)}^k\right]=\sum _{i=0}^k\left(\begin{array}{l}k\\ i\end{array}\right)E\left(x^i\right){\mu }^{k-i}$$

---

一、计算$E[(x-\mu {)}^k]$

（不会算）

$E[(x-\mu {)}^k]$为$X$的$k$阶中心矩，
$$E(X-E(X){)}^k=E{\left(X-\mu \right)}^k=\sum _{i=0}^k\left(\begin{array}{l}k\\ i\end{array}\right)E\left(x^i\right){\left(-\mu \right)}^{k-i},$$