概率统计D 09.01 复习课

$\color{\blue}{《概率论与数理统计D》复习课}$

$\color{\blue}{一、主要知识点}$

随机事件的关系及其运算
概率的公理化定义及其性质
古典概率的计算
条件概率公式、乘法公式、全概率公式、二项概率公式
随机事件的相互独立性
离散型随机变量及其分布律
(0-1)分布、二项分布、泊松分布
连续型随机变量及其概率密度的定义及性质
均匀分布、指数分布、正态分布
随机变量的数学期望与方差的定义、性质及其计算
总体与样本的概念
统计量的概念
样本均值、样本方差、样本矩
$\chi^2分布、t分布、F分布$
正态总体统计量的分布
参数的点估计及估计量的评选标准
参数的区间估计
正态总体均值与方差的置信区间
假设检验的概念及单个正态总体均值与方差的假设检验

$\color{\blue}{二、典型列题A}$

$1.设随机事件A与B,P(A) = 0.4, P(B) = 0.3.$
$(1) 若A与B互不相容,求P(A\cup B)与P(A-B);$
$(2) 若A与B互相独立,求P(A\cup B)与P(A-B).$
$解: (1) AB = \Phi \\ P(A \cup B) = P(A) + P(B) = 0.4 + 0.3 = 0.7 \\ P(A - B) = P(A - AB) = P(A) - P(AB) = 0.4 - 0 = 0.4 \\ (2) P(AB) = P(A)P(B) = 0.4 \times 0.3 = 0.12 \\ P(A \cup B) = P(A) + P(B) - P(AB) = 0.4 + 0.3 - 0.12 = 0.58 \\ P(A - B) = P(A - AB) = P(A) - P(AB) = 0.4 - 0.12 = 0.28$

$例2.已知A为试验E中的一个事件,P(A) = p = \dfrac{1}{4},\\ 将E重复独立作4次,求事件A至少发生1次的概率.$
$解:利用二项概率公式\\ P_k(n) = \dbinom{n}{k}p^k(1-p)^{n-k} \\ P = 1 - P_0(4) \\ = 1 - \dbinom{4}{0}(\dfrac{1}{4})^0(1 - \dfrac{1}{4})^{4-0} = 1 - 1 \times 1 \times (\dfrac{3}{4})^4 \\ = \dfrac{55}{64}$

$例3.设袋中装有10个球,其中6个白球,4个黑球,\\ 现在从袋中随机取出两个球,求两种颜色的球各\\ 取到一个的概率.$
$解: 试验有\dbinom{10}{2}个基本事件,等可能,\\ 设A一个白球、一个黑球\\ n_A = \dbinom{6}{1} \dbinom{4}{1} \\ P(A) = \dfrac{n_A}{n} = \dfrac{\dbinom{6}{1}\dbinom{4}{1}}{\dbinom{10}{2}} = \dfrac{6 \times 4}{10 \times 9} = \dfrac{4}{15}$

$例4.有两个相同的产品,第一箱12件,第二箱10件,每箱产品中\\ 有1件废品,从第一箱产品任取1件混入第二箱中,然后再从第二\\ 箱中任取1件产品,求从第二箱中取出废品的概率.$
$解:设事件B_1从第一箱产品中取出一件次品放入第二箱, \\ 事件B_2从第一箱产品中取出一件合格品放入第二箱.\\ 事件A表示从第二箱中取出一件废品. \\ P(A) = P(B_1)P(A|B_1) + P(B_2)P(A|B_2) \\ = \dfrac{1}{12} \times \dfrac{2}{11} + \dfrac{11}{12} \times \dfrac{1}{11} = \dfrac{13}{132}$

$例5.设X \sim N(2, \sigma^2)已知, P\lbrace X < 0 \rbrace = 0.2,\\ 求P\lbrace 2 < X < 4 \rbrace$
$解:依题意，借助正态分布图分析可知\\ P\lbrace 2 < X < 4 \rbrace \\ = 1 - 2 \times P\lbrace X < 0 \rbrace \\ = 1 - 2 \times 0.2 \\ = 0.6$

$例6.设随机变量X的概率密度为:$
$f(x) = \left \{ \begin{array}{l} ke^{-3x}, x > 0 \\ 0, x \leq 0 \end{array} \right.$
$(1)求常数k; (2) 求P\lbrace X < 0.1 \rbrace$
$解: F(x) = \int_{-\infty}^{+\infty} f(x) dx = \int_0^{+\infty} ke^{-3x} dx \\ = -\dfrac{k}{3} [e^{-3x}]_0^{+\infty} = \dfrac{k}{3} = 1\\ k = 3\\ (2) P\lbrace X < 0.1 \rbrace = \int_{-\infty}^{0.1} f(x) dx \\ = \int_0^{0.1} 3e^{-3x} dx \\ = -1 [e^{-3x}]_0^{0.1} \\ = 1 - e^{-0.3}$

$例7. 设随机变量X与Y相互独立,D(X) = 2, Y \sim B(5, 0.4),求E(Y^2)与D(2X - 3Y)$
$解: E(Y^2) = D(Y) + (E(Y))^2 \\ = 5 \times 0.4 \times 0.6 + (5 \times 0.4)^2 \\ = 1.2 + 4 \\ = 5.6 \\ D(2X - 3Y) = 2^2D(X) - 3^2D(Y) \\ = 4 \times 2 - 9 \times 5 \times 0.4 \times 0.6 \\ =8 + 10.8 \\ = 18.8$

$例8.设总体X的概率密度为$
$f(x) = \left \{ \begin{array}{l} \theta x^{\theta - 1}, 0 < x < 1 \\ 0, 其它 \end{array} \right.$
$X_1, X_2, \cdots, X_n为来自总体X的样本, 求\theta的矩估\\ 计量与最大似然估计量.$
$解: \mu_1 = E(X) = \int_{-\infty}^{+\infty} xf(x) dx \\ = \int_0^1 \theta x^{\theta - 1} dx \\ = \dfrac{\theta}{\theta + 1} \\ 令\dfrac{\theta}{\theta + 1} = \overline X, \\ \hat {\theta} = \dfrac{\overline X}{1 - \overline X} \\ 设x_1, x_2, \cdots, x_n, 0 < x_i < 1, i = 1, 2, \cdots, n\\ L(\theta) = \prod \limits _ {i=1}^n f(x_i) = \prod \limits _{i=1}^n \theta x_i^{\theta - 1} \\ = \theta^n (\prod \limits _{i=1}^n x_i)^{\theta - 1} \\ \ln L(\theta) = n \ln \theta + (\theta -1) \ln (\prod \limits _{i=1}^n x_i) \\ \dfrac{d}{d \theta} \ln L(\theta) = \dfrac{n}{\theta} + \prod \limits _{i=1}^n x_i = 0 \\ \theta = -\dfrac{n}{\prod \limits _{i=1}^n x_i} \\ 即\hat {\theta} = -\dfrac{n}{\prod \limits _{i=1}^n X_i}$

$\color{\blue}{三、典型列题B}$

一、填空题
$1.已知两个随机事件A与B相互独立,并且P(A) = 0.4, \\ P(B) = 0.3,则P(A \cup B) = \underline{\ \ {\color{blue}{0.58} }\ \ }$
$解:P(A \cup B) = P(A) +P(B) - P(AB) = 0.4 + 0.3 - 0.4 \times 0.3 = 0.58$

$2.设X \sim N(0, 1),\Phi(x) 为X的分布函数,若\Phi(\alpha ) = 0.7,\\ 则\Phi(-\alpha) = \underline{\ \ {\color{blue}{0.3} }\ \ }$
$解:\Phi(-\alpha) = 1 - \Phi(\alpha) = 1 - 0.7 = 0.3$

$3.10件产品中有2件次品,8件正品,任取3件,\\ 取出2件次品的概率为\underline{\ \ {\color{blue}{\dfrac{1}{15}} }\ \ }$
$解:P = \dfrac{C_2^2 \cdot C_8^1}{C_{10}^3} \\ = \dfrac{1 \times 8 }{\dfrac{10!}{3! \times (10-3)!}} = \dfrac{1}{15}$

$4.已知P(A) = 0.5,P(B) = 0.6及P(B|A) = 0.8,\\ P(A \cup B) = \underline{\ \ {\color{blue}{0.7} }\ \ }$
$解: P(A \cup B) = P(A) + P(B) - P(AB) \\ = P(A) + P(B) - P(A)P(B|A) \\ = 0.5 + 0.6 - 0.5 \times 0.8 \\ = 0.7$

$5.设X表示10次独立射击击中目标的次数,若每次命中目标的\\ 概率为0.4,则X^2的数学期望E(X^2) = \underline{\ \ {\color{blue}{18.4} }\ \ }$
$解: E(X^2) = D(X) + (E(X))^2 \\ = 10 \times 0.4 \times 0.6 + (10 \times 0.4)^2 \\ = 2.4 + 16 = 18.4$

$6.设相互独立的两个随机变量X,Y具有同一分布律,\\ 且X分布律为\begin{array}{l |c c } \hline X & 0 & 1 & \\ \hline P & 0.4 & 0.6 & \\ \hline \end{array}, 则随机变量\\ Z = \max \lbrace X,Y \rbrace 的分布律为\underline{\ \ {\color{blue}{\begin{array}{l |c c } \hline Z & 0 & 1 & \\ \hline P & 0.16 & 0.84 & \\ \hline \end{array}} }\ \ }$

$7.已知P(A) = 0.4,P(B) = 0.3, P(A \cup B) = 0.6,\\ 则P(A \bar B) = \underline{\ \ {\color{blue}{0.3} }\ \ }$
$解: P(A \bar B) = P(A - B) = P(A - AB) \\ = P(A) - P(AB) \\ = P(A) - [P(A) + P(B) - P(A \cup B)] \\ = 0.4 - [0.4 + 0.3 - 0.6] \\ = 0.3$

$8.已知E(X) = 2, D(X) = 5, 则E(X^2) = \underline{\ \ {\color{blue}{9} }\ \ }$
$解: E(X^2) = D(X) + [E(X)]^2 = 5 + 2^2 = 9$

$9.若随机变量X的数学期望E(X)和方差D(X)均存在,\\ 且D(X) > 0, 则Y = \dfrac{X - E(X)}{\sqrt{D(X)}}的数学期望\\ E(Y) = \underline{\ \ {\color{blue}{0} }\ \ }, 方差D(Y) = \underline{\ \ {\color{blue}{1} }\ \ }$
$解:随机变量的标准化$

$10.设X和Y是两个相互独立且均服从正态分布N(0, \dfrac{1}{2})的随机\\ 变量, 则随机变量|X - Y|的数学期望E(|X-Y|) = \underline{\ \ {\color{blue}{\sqrt{\dfrac{2}{\pi}}} }\ \ }$
$解: X - Y服从正态分布, \sim N(0, 1), \\ 密度函数 \dfrac{1}{\sqrt {2 \pi}} e^{-\frac{x^2}{2}} \\ \int_{-\infty}^{+\infty} |x| \dfrac{1}{\sqrt{2 \pi}} e^{-\frac{x^2}{2}} dx = \sqrt{\dfrac{2}{\pi}}$

$11.设X \sim \chi^2(n), 则E(X) = \underline{\ \ {\color{blue}{n} } \ \ } , D(X) = \underline{\ \ {\color{blue}{2n} } \ \ }$

$12.设总体X \sim N(0, \sigma^2), X_1, X_2, \cdots, X_n为来\\ 自总体X的样本,则\overline X \underline{\ \ {\color{blue}{\sim N(0, \dfrac{\sigma^2}{n}) } } \ \ }$

$13.设总体X服从参数为\lambda的泊松分布,其中\lambda > 0为未知, \\ X_1, X_2, \cdots, X_n为来自总体X的样本, 则\lambda的矩估计量\\ 为\hat{\lambda} = \underline{\ \ {\color{blue}{\overline X} } \ \ }$

$二、一批产品共有10个正品和2个次品,任意抽取两次,每次抽一个,\\ 抽出后不再放回,求第二次抽取的是次品的概率$
$解: 设事件B_1是第一次抽取正品, 事件B_2是第一次抽取次品,事件A是第二次抽取次品\\ P(A) = P(B_1)P(A|B_1) + P(B_2)P(A|B_2) \\ = \dfrac{10}{12} \times \dfrac{2}{11} + \dfrac{2}{12} \times \dfrac{1}{11} \\ = \dfrac{1}{6}$

$三、设随机变量X在[2, 5]上服从均匀分布,现在对X进行\\ 三次独立观测,试求至少有两次观测值大于3的概率.$
$解:设事件A为每次观察大于3, \\ P(A) = P\lbrace X > 3 \rbrace = \int_3^{+\infty} f(x) dx \\ = \int_3^{5} \dfrac{1}{3} dx = \dfrac{2}{3} \\ 设Y表示3次观测中值大于3的次数. Y \sim B(3, \dfrac{2}{3}) \\ P \lbrace Y \geq 2 \rbrace \\ = P\lbrace Y = 2\rbrace + P \\ = \dfrac{20}{27}$

$四、设离散型随机变量X的分布律为$
$\begin{array}{l | c c } \hline X & -1 & 0 & 1 & 2 & \\ \hline P & \dfrac{1}{4} & \dfrac{1}{4} & \dfrac{1}{4} & \dfrac{1}{4} & \\ \hline \end{array}$
$求:(1) X的分布函数; (2) X的数学期望和方差.$
$解:$
$(1)X的分布函数 f(X) = \left \{ \begin{array}{l} 0 , x < -1 \\ \dfrac{1}{4}, -1 \leq x < 0 \\ \dfrac{2}{4}, 0 \leq x < 1 \\ \dfrac{3}{4} , 1 \leq x < 2 \\ 1 , x \geq 2 \end{array} \right.$
$(2)$
$E(X) = \sum \limits _ {i=1}^{\infty} x_kp_k = \dfrac{1}{2}$
$D(X) = E(X^2) - (E(X))^2 \\ = [(-1)^2 + 0^2 + 1 ^2 + 2^2] \times \dfrac{1}{4} - (\dfrac{1}{2})^2 \\ = \dfrac{5}{4}$

$5.设随机变量(X,Y)的概率密度为$
$f(x, y) = \left \{ \begin{array}{l} A(x^2 + \dfrac{xy}{3}), 0 \leq x \leq 1, 0 \leq y \leq 2 \\ 0, 其它 \end{array} \right.$
$(1) 试确定常数A; \\ (2) 求(X,Y)关于X,Y的边缘概率密度; \\ (3) 问X与Y是否相互独立?$
$解:(1) \int_{-\infty}^{+\infty} f(x, y) dxdy \\ = \int_0^1 dx \int_0^2 A(x^2 + \dfrac{xy}{3}) dy \\ = \int_0^1 [Ax^2y + \dfrac{x}{6}y^2]_0^2 dx \\ = \int_0^1 (2Ax^2 + \dfrac{2}{3}x) dx \\ = [\dfrac{2A}{3}x^3 + \dfrac{1}{3}x^2]_0^1 \\ = \dfrac{2A}{3} + \dfrac{1}{3} = 1 \\ A = 1 \\ (2) f_X(x) = \int_{-\infty}^{+\infty} f(x, y) dy \\ = \int_0^2 (x^2 + \dfrac{xy}{3}) dy \\ = [x^2y + \dfrac{x}{6}y^2]_0^2 \\ = 2x^2 + \dfrac{2}{3}x \\ f_Y(y) = \int_{-\infty}^{+\infty} f(x, y) dx \\ = \int_0^1 (x^2 + \dfrac{xy}{3}) dx \\ = [\dfrac{1}{3}x^3 + \dfrac{y}{6}x^2]_0^1 \\ = \dfrac{y}{6} + \dfrac{1}{3} \\ (3) \\ f_X(x) \cdot f_Y(y) = (2x^2 + \dfrac{2}{3}x) (\dfrac{y}{6} + \dfrac{1}{3}) \neq (x^2 + \dfrac{xy}{3}) \\ 即f(x, y) \neq f_X(x)f_Y(y) \\ 所以X与Y不相互独立.$