数理统计中的一些统计量

总体 $X$
简单随机样本 $X_i(i=1,2,...,n)$：

1. 每个个体与总体同分布
2. 各个体之间相互独立（independent and identically distributed, i.i.d.）

伽马函数$\Gamma (\gamma )$：
$$\Gamma (\gamma )={\int }_0^{+\infty }{x}^{\gamma -1}{\text{e}}^{-x}dx$$

一、样本数字特征和样本矩

样本均值：
$$\overline{X}=\frac{1}{n}\sum _{i=1}^n{X}_i$$
样本方差：
$$S^2=\frac{1}{n-1}\sum _{i=1}^n(X_i-\overline{X}{)}^2$$
样本标准差：
$$S=\sqrt{\frac{1}{n-1}\sum _{i=1}^n(X_i-\overline{X}{)}^2},S=\sqrt{S^2}$$
样本$k$阶中心矩：
$$A_k=\frac{1}{n}\sum _{i=1}^n{X}_i^k$$
样本$k$阶原点矩：
$$B_k=\frac{1}{n}\sum _{i=1}^n(X_i-\overline{X}{)}^k$$

二、抽样分布

1. ${\chi }^2$分布(chi-squared distribution)
   定义：
   $${\chi }^2=\sum _{i=1}^n{X}_i^2,X_i\sim N(0,1)$$
   概率密度函数$(probabilitydensityfunction,pdf)$:
   $$f(x)=\{\begin{array}{rlr}\frac{1}{2^{n/2}\Gamma \left(n/2\right)}{x}^{(n/2)-1}{\mathrm{e}}^{-n/2}& ,& x\ge 0,\\ & & \\ 0& ,& x<0.\end{array}$$
   

2. $t$分布(Student’s distribution)
   定义：
   $$T=\frac{X}{\sqrt{Y/n}},X\sim N(0,1),Y\sim {\chi }^2(n)$$
   概率密度函数:
   $$f(t)=\frac{\Gamma ((n+1)/2)}{\sqrt{n\pi }\Gamma (n/2)}(1+t^2/n{)}^{-(n-1)/2}.$$
   

3. $F$分布(F-distribution, Ronald.A.Fisher)
   定义：
   $$F=\frac{U/n_1}{V/n_2},U\sim {\chi }^2(n_1),V\sim {\chi }^2(n_2),U,V相互独立$$
   概率密度函数:
   $$f(y)=\{\begin{array}{rlr}\frac{\Gamma ((n_1+n_2)/2)}{\Gamma (n_1/2)\Gamma (n_2/2)}(n_1/n_2{)}^{n_1/2}{y}^{(n_1/2)-1}(1+n_{1}y/n_2{)}^{-(n_1+n_2)/2}& ,& y\ge 0,\\ & & \\ 0& ,& y<0.\end{array}$$
   概率密度函数生成代码

# -*- coding: utf-8 -*-
"""
Created on Sat Nov 14 19:28:14 2020

@author   : MrX_OvO
@email    : 1176471624@qq.com
@copyright: MrX_OvO Sat Nov 14 19:28:14 2020

To:
    One is never too old to learn.

####################################################################
//                          _ooOoo_                               //
//                         o8888888o                              //
//                         88" . "88                              //
//                         (| ^_^ |)                              //
//                         O\  =  /O                              //
//                      ____/`---'\____                           //
//                    .'  \\|     |//  `.                         //
//                   /  \\|||  :  |||//  \                        //
//                  /  _||||| -:- |||||-  \                       //
//                  |   | \\\  -  /// |   |                       //
//                  | \_|  ''\---/''  |   |                       //
//                  \  .-\__  `-`  ___/-. /                       //
//                ___`. .'  /--.--\  `. . ___                     //
//              ."" '<  `.___\_<|>_/___.'  >'"".                  //
//            | | :  `- \`.;`\ _ /`;.`/ - ` : | |                 //
//            \  \ `-.   \_ __\ /__ _/   .-` /  /                 //
//      ========`-.____`-.___\_____/___.-`____.-'========         //
//                           `=---='                              //
//      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^        //
//             佛祖保佑      永不宕机      永无BUG                //
####################################################################
"""


import numpy as np

def colors(plot_nums = 7):
    color = []
    for i in range(plot_nums):
        color.append(np.random.rand(1, 3).tolist()[0])
    return color

def labels(plot_nums = 7, types = 'chi2'):
    labels = []
    for i in range(plot_nums):
        if types == 'F':
            labels.append(r'n1=%i,n2=%i' %(i ** 4 + 10, (i + 2) * 20))
        else:
            labels.append(r'n=%i' % (i + 1))
    return labels

def plot(color, labels, types = 'chi2',plot_nums = 7, p = 10e-8):
    import matplotlib.pyplot as plt
    from scipy import stats as st
    size, fsize = 3000, (16, 9)
    t0 = int(size / plot_nums * .164)
    fig, ax = plt.subplots(figsize=fsize)
    x = np.linspace(st.chi2.ppf(p, plot_nums), st.chi2.ppf(1 - p, plot_nums), size)
    if types == 'Student':
        x = np.linspace(st.t.ppf(p, plot_nums), st.t.ppf(1 - p, plot_nums), size)
    elif types == 'F':
        x = np.linspace(
            st.f.ppf(p, (plot_nums - 1) ** 4 + 10, (plot_nums + 1) * 20),
            st.f.ppf(1 - p, (plot_nums - 1 )** 4 + 10, (plot_nums + 1) * 20),
            size)
    connstyle=[]
    for i in range(plot_nums):
        connstyle.append(r'arc3, rad = .%i' %((plot_nums - i) / 5))
    for i in range(plot_nums):
        y = st.chi2.pdf(x, i + 1)
        text = r'n=%i' %(i + 1)
        x_, y_ = x[(i + 1) * t0], y[(i + 1) * t0]
        if types == 'Student':
            t = int(size / 2)
            y = st.t.pdf(x, i + 1)
            x_, y_ = x[t], y[t]
        elif types == 'F':
            t = int(size / 6)
            y = st.f.pdf(x, i ** 4 + 10, (i + 2) * 20)
            x_, y_ = x[t], y[t]
            text = r'n1=%i,n2=%i' %(i ** 4 + 10, (i + 2) * 20)
        ax.plot(x, y, color = color[i])
        ax.annotate(text, xy = (x_, y_),
                    xytext = ((plot_nums - i + 1) / plot_nums * 80,
                              (plot_nums - i + 1) / plot_nums * 10),
                    textcoords = 'offset points',
                    arrowprops = dict(arrowstyle = '->',
                                      connectionstyle = connstyle[i],
                                      color = color[i],
                                      ),
                    )
    ax.set_xlabel('x')
    ax.set_ylabel('y=f(x)')
    ax.set_xlim(-0.1, 20)
    ax.set_ylim(-0.001, 0.5)
    ax.legend(labels)
    ax.set_title(r'pdf of %s' %types)
    if types == 'Student':
        #data表示通过值来设置x轴的位置，将x轴绑定在y=0的位置
        ax.spines['bottom'].set_position(('data',0))
        #axes表示以百分比的形式设置轴的位置，即将y轴绑定在x轴50%的位置，也就是x轴的中点
        ax.spines['left'].set_position(('axes',0.5))
        #设置图片的右边框和上边框为不显示
        ax.spines['right'].set_color('none')
        ax.spines['top'].set_color('none')
        ax.set_xlim(-5, 5)
        ax.set_ylim(-0.01, 0.4)
    elif types == 'F':
        ax.set_xlim(-0.01, 5)
        ax.set_ylim(-0.01, 2)
    plt.savefig(r'C:/Users/MrX/Desktop/homework/spyder_test/%s.png' %types)
    plt.show()

def main():
    type1, type2 = 'Student', 'F'
    plot_nums1, plot_nums2 = 5, 3
    color0, color1, color2 = colors(), colors(plot_nums1), colors(plot_nums2)
    labels0, labels1, labels2 = labels(), labels(plot_nums1), labels(plot_nums2, type2)
    # chi2
    plot(color0, labels0)
    # Student
    plot(color1, labels1, type1, plot_nums1)
    # F
    plot(color2, labels2, type2, plot_nums2)

if __name__ == '__main__':
    main()