当前位置:网站首页>【九阳神功】2016复旦大学应用统计真题+解析
【九阳神功】2016复旦大学应用统计真题+解析
2022-07-06 09:20:00 【大师兄统计】
真题部分
一、(15分) 三个人独立地同时破译密码, 且三人能破译密码的概率分别为1/5, 1/3和1/4, 求此密码能够被破译的概率.
二、(15分) 从(0,1)中随机地取两个数, 求其积不小于3/16且其和不大于1的概率.
三、(15分) X ∼ N ( 0 , 1 ) , X \sim N(0,1), X∼N(0,1), 求 Y = X 2 Y=X^{2} Y=X2 的密度函数.
四、(30分) 记(0,1),(1,0),(0,0)三点围成的区域为 D , ( X , Y ) D,(X, Y) D,(X,Y)服从 D D D上的均匀分布, 求
(1)(15分) E ( X + Y ) , Var ( X + Y ) E(X+Y), \operatorname{Var}(X+Y) E(X+Y),Var(X+Y);
(2)(15分) X , Y X, Y X,Y 的相关系数.
五、(15分) 对于两个只有两个取值的随机变量 X , Y , X, Y, X,Y, 试证明 X , Y X, Y X,Y独立当且仅当 X , Y X, Y X,Y不相关.
六、(15分) 设有来自总体 X ∼ N ( μ , σ 2 ) X \sim N\left(\mu, \sigma^{2}\right) X∼N(μ,σ2)的 2 n 2 n 2n个随机样本, 试求期望
E ( ∑ i = 1 n ( X i + X n + i − 2 X ˉ ) 2 ) . E\left(\sum_{i=1}^{n}\left(X_{i}+X_{n+i}-2 \bar{X}\right)^{2}\right). E(i=1∑n(Xi+Xn+i−2Xˉ)2).
七、(15分) X 1 , X 2 , X 3 X_{1}, X_{2}, X_{3} X1,X2,X3是i.i.d.的服从 U ( 0 , 1 ) U(0,1) U(0,1)的随机变量, 求次序统计量 X ( 1 ) X_{(1)} X(1)的分布函数与期望.
八、(30分) 有来自 X ∼ f ( x ) = { θ , 0 ≤ x < 1 1 − θ , 1 ≤ x < 2 , 0 , otherwise X \sim f(x)=\left\{\begin{array}{cl}\theta, & 0 \leq x<1 \\ 1-\theta, & 1 \leq x<2, \\ 0, & \text { otherwise }\end{array}\right. X∼f(x)=⎩⎨⎧θ,1−θ,0,0≤x<11≤x<2, otherwise 的 n n n 个简单随机样本, 求
(1)(15分) θ \theta θ 的矩估计;
(2)(15分) θ \theta θ 的最大似然估计, 已知 m = ∑ i = 1 n I [ X i < 1 ] m=\sum_{i=1}^{n} I\left[X_{i}<1\right] m=∑i=1nI[Xi<1].
解析部分
一、(15分) 三个人独立地同时破译密码, 且三人能破译密码的概率分别为1/5, 1/3和1/4, 求此密码能够被破译的概率.
Solution: 根据德摩根公式, P { 至少有一人破译 } = 1 − P { 没有一个人破译 } = 1 − 4 5 × 2 3 × 3 4 = 0.6. \begin{aligned} P\{\text { 至少有一人破译 }\} &=1-P\{\text { 没有一个人破译 }\} \\ &=1-\frac{4}{5} \times \frac{2}{3} \times \frac{3}{4}=0.6 . \end{aligned} P{ 至少有一人破译 }=1−P{ 没有一个人破译 }=1−54×32×43=0.6.
二、(15分) 从(0,1)中随机地取两个数, 求其积不小于3/16且其和不大于1的概率.
Solution: 设取到的两个数是 X , Y ∼ U ( 0 , 1 ) X, Y \sim U(0,1) X,Y∼U(0,1), 其积不小于 3 16 \frac{3}{16} 163 意味着 X Y ≥ 3 16 X Y \geq \frac{3}{16} XY≥163, 其和不大于 1 意味着 X + Y ≤ 1 X+Y \leq 1 X+Y≤1.
令 D = { ( x , y ) : x y ≥ 3 16 , x + y ≤ 1 } ∩ ( 0 , 1 ) 2 D=\left\{(x, y): x y \geq \frac{3}{16}, x+y \leq 1\right\} \cap(0,1)^{2} D={ (x,y):xy≥163,x+y≤1}∩(0,1)2, 该概率为 ∫ D f ( x , y ) d x d y = 1 8 − ∫ 1 4 3 4 ∫ 1 4 3 16 x d y d x = 1 8 − ∫ 1 4 3 4 ( 3 16 x − 1 4 ) d x = 1 4 − 3 ln 3 16 \int_{D} f(x, y) d x d y=\frac{1}{8}-\int_{\frac{1}{4}}^{\frac{3}{4}} \int_{\frac{1}{4}}^{\frac{3}{16 x}} d y d x=\frac{1}{8}-\int_{\frac{1}{4}}^{\frac{3}{4}}\left(\frac{3}{16 x}-\frac{1}{4}\right) d x=\frac{1}{4}-\frac{3 \ln 3}{16} ∫Df(x,y)dxdy=81−∫4143∫4116x3dydx=81−∫4143(16x3−41)dx=41−163ln3
三、(15分) X ∼ N ( 0 , 1 ) , X \sim N(0,1), X∼N(0,1), 求 Y = X 2 Y=X^{2} Y=X2 的密度函数.
Solution: 当 y ≥ 0 y \geq 0 y≥0 时,
F ( y ) = P { Y ≤ y } = P { X 2 ≤ > y } = P { − y ≤ X ≤ y } = 2 Φ ( y ) − 1 F(y)=P\{Y \leq y\}=P\left\{X^{2} \leq>y\right\}=P\{-\sqrt{y} \leq X \leq \sqrt{y}\}=2 \Phi(\sqrt{y})-1 F(y)=P{ Y≤y}=P{ X2≤>y}=P{ −y≤X≤y}=2Φ(y)−1, 故
f Y ( y ) = F ′ ( y ) = 2 φ ( y ) ⋅ 1 2 y = 1 2 π y e − y 2 , y ≥ 0 f_{Y}(y)=F^{\prime}(y)=2 \varphi(\sqrt{y}) \cdot \frac{1}{2 \sqrt{y}}=\frac{1}{\sqrt{2 \pi y}} e^{-\frac{y}{2}}, y \geq 0 fY(y)=F′(y)=2φ(y)⋅2y1=2πy1e−2y,y≥0
四、(30分) 记(0,1),(1,0),(0,0)三点围成的区域为 D , ( X , Y ) D,(X, Y) D,(X,Y)服从 D D D上的均匀分布, 求
(1)(15分) E ( X + Y ) , Var ( X + Y ) E(X+Y), \operatorname{Var}(X+Y) E(X+Y),Var(X+Y);
(2)(15分) X , Y X, Y X,Y 的相关系数.
Solution: (1) E ( X + Y ) = 2 ∫ 0 1 ∫ 0 1 − y ( x + y ) d x d y = ∫ 0 1 ( 1 − y 2 ) d y = 1 − 1 3 = 2 3 E(X+Y)=2 \int_{0}^{1} \int_{0}^{1-y}(x+y) d x d y=\int_{0}^{1}\left(1-y^{2}\right) d y=1-\frac{1}{3}=\frac{2}{3} E(X+Y)=2∫01∫01−y(x+y)dxdy=∫01(1−y2)dy=1−31=32, E ( X + Y ) 2 = 2 ∫ 0 1 ∫ 0 1 − y ( x + y ) 2 d x d y = 2 3 ∫ 0 1 ( 1 − y 3 ) d y = 2 3 ( 1 − 1 4 ) = 1 2 , E(X+Y)^{2}=2 \int_{0}^{1} \int_{0}^{1-y}(x+y)^{2} d x d y=\frac{2}{3} \int_{0}^{1}\left(1-y^{3}\right) d y=\frac{2}{3}\left(1-\frac{1}{4}\right)=\frac{1}{2}, E(X+Y)2=2∫01∫01−y(x+y)2dxdy=32∫01(1−y3)dy=32(1−41)=21, 因此
Var ( X + Y ) = 1 2 − 4 9 = 1 18 . \operatorname{Var}(X+Y)=\frac{1}{2}-\frac{4}{9}=\frac{1}{18}. Var(X+Y)=21−94=181.(2) E X Y = 2 ∫ 0 1 ∫ 0 1 − y x y d x d y = ∫ 0 1 ( y 3 − 2 y 2 + y ) d y = 1 4 − 2 3 + 1 2 = 1 12 E X Y=2 \int_{0}^{1} \int_{0}^{1-y} x y d x d y=\int_{0}^{1}\left(y^{3}-2 y^{2}+y\right) d y=\frac{1}{4}-\frac{2}{3}+\frac{1}{2}=\frac{1}{12} EXY=2∫01∫01−yxydxdy=∫01(y3−2y2+y)dy=41−32+21=121, E X = E Y = 2 ∫ 0 1 ∫ 0 1 − y x d x d y = ∫ 0 1 ( y 2 − 2 y + 1 ) d y = 1 3 − 1 + 1 = 1 3 , E X=E Y=2 \int_{0}^{1} \int_{0}^{1-y} x d x d y=\int_{0}^{1}\left(y^{2}-2 y+1\right) d y=\frac{1}{3}-1+1=\frac{1}{3}, EX=EY=2∫01∫01−yxdxdy=∫01(y2−2y+1)dy=31−1+1=31, 故
Cov ( X , Y ) = 1 12 − 1 9 = − 1 36 . \operatorname{Cov}(X, Y)=\frac{1}{12}-\frac{1}{9}=-\frac{1}{36}. Cov(X,Y)=121−91=−361. E X 2 = 2 ∫ 0 1 ∫ 0 1 − y x 2 d x d y = 2 3 ∫ 0 1 ( 1 − y ) 3 d y = 1 6 , E X^{2}=2 \int_{0}^{1} \int_{0}^{1-y} x^{2} d x d y=\frac{2}{3}\int_{0}^{1}(1-y)^{3} d y=\frac{1}{6}, EX2=2∫01∫01−yx2dxdy=32∫01(1−y)3dy=61, 故 Var ( X ) = Var ( Y ) = 1 6 − 1 9 = 1 18 , \operatorname{Var}(X)=\operatorname{Var}(Y)=\frac{1}{6}-\frac{1}{9}=\frac{1}{18}, Var(X)=Var(Y)=61−91=181,进而有 ρ X Y = − 1 2 \rho_{X Y}=-\frac{1}{2} ρXY=−21.
五、(15分) 对于两个只有两个取值的随机变量 X , Y , X, Y, X,Y, 试证明 X , Y X, Y X,Y独立当且仅当 X , Y X, Y X,Y不相关.
Solution:
X = x 1 X=x_{1} X=x1 | X = x 2 X=x_{2} X=x2 | ||
---|---|---|---|
Y = y 1 Y=y_{1} Y=y1 | p 11 p_{11} p11 | p 21 p_{21} p21 | 1 − q 1-q 1−q |
Y = y 2 Y=y_{2} Y=y2 | p 12 p_{12} p12 | p 22 p_{22} p22 | q q q |
1 − p 1-p 1−p | p p p |
Solution: 独立一定不相关, 只需证明充分性. 不妨仅讨论 X ′ = X − x 1 x 2 − x 1 X'=\frac{X-x_1}{x_2-x_1} X′=x2−x1X−x1, Y ′ = Y − y 1 y 2 − y 1 Y'=\frac{Y-y_1}{y_2-y_1} Y′=y2−y1Y−y1, X , Y X,Y X,Y不相关与 X ′ , Y ′ X',Y' X′,Y′不相关是等价的. 当 X ′ , Y ′ X',Y' X′,Y′不相关时, 说明 p 22 = E ( X ′ Y ′ ) = E ( X ′ ) E ( Y ′ ) = p q , p_{22}=E(X'Y')=E(X')E(Y')=pq, p22=E(X′Y′)=E(X′)E(Y′)=pq,进一步有 p 21 = p − p 22 = p − p q = p ( 1 − q ) , p_{21}=p-p_{22}=p-pq=p(1-q), p21=p−p22=p−pq=p(1−q), p 12 = q − p 22 = q − p q = q ( 1 − p ) , p_{12}=q-p_{22}=q-pq=q(1-p), p12=q−p22=q−pq=q(1−p), p 11 = 1 − p − p 12 = ( 1 − p ) − q ( 1 − p ) = ( 1 − p ) ( 1 − q ) . p_{11}=1-p-p_{12}=(1-p)-q(1-p)=(1-p)(1-q). p11=1−p−p12=(1−p)−q(1−p)=(1−p)(1−q). 因此 X ′ , Y ′ X',Y' X′,Y′独立, 故 X , Y X,Y X,Y也独立.
六、(15分) 设有来自总体 X ∼ N ( μ , σ 2 ) X \sim N\left(\mu, \sigma^{2}\right) X∼N(μ,σ2)的 2 n 2 n 2n个随机样本, 试求期望
E ( ∑ i = 1 n ( X i + X n + i − 2 X ˉ ) 2 ) . E\left(\sum_{i=1}^{n}\left(X_{i}+X_{n+i}-2 \bar{X}\right)^{2}\right). E(i=1∑n(Xi+Xn+i−2Xˉ)2).
Solution: 记 Y i = X i + X n + i , i = 1 , 2 , … , n Y_{i}=X_{i}+X_{n+i}, i=1,2, \ldots, n Yi=Xi+Xn+i,i=1,2,…,n, 这样 Y 1 , Y 2 , … , Y n Y_{1}, Y_{2}, \ldots, Y_{n} Y1,Y2,…,Yn 就是来自于总体 N ( 2 μ , 2 σ 2 ) N\left(2 \mu, 2 \sigma^{2}\right) N(2μ,2σ2) 的 n n n 个随机样本, Y ˉ = 2 X ˉ \bar{Y}=2 \bar{X} Yˉ=2Xˉ, 根据样本方差的定义和性质, 我们有 1 2 σ 2 ∑ i = 1 n ( X i + X n + i − 2 X ˉ ) 2 = 1 2 σ 2 ∑ i = 1 n ( Y i − Y ˉ ) 2 ∼ χ 2 ( n − 1 ) \frac{1}{2 \sigma^{2}} \sum_{i=1}^{n}\left(X_{i}+X_{n+i}-2 \bar{X}\right)^{2}=\frac{1}{2 \sigma^{2}} \sum_{i=1}^{n}\left(Y_{i}-\bar{Y}\right)^{2} \sim \chi^{2}(n-1) 2σ21i=1∑n(Xi+Xn+i−2Xˉ)2=2σ21i=1∑n(Yi−Yˉ)2∼χ2(n−1) 因此
E ∑ i = 1 n ( X i + X n + i − 2 X ˉ ) 2 = 2 ( n − 1 ) σ 2 . E \sum_{i=1}^{n}\left(X_{i}+X_{n+i}-2 \bar{X}\right)^{2}=2(n-1)\sigma^{2}. Ei=1∑n(Xi+Xn+i−2Xˉ)2=2(n−1)σ2.
七、(15分) X 1 , X 2 , X 3 X_{1}, X_{2}, X_{3} X1,X2,X3, 是i.i.d.的服从 U ( 0 , 1 ) U(0,1) U(0,1)的随机变量, 求次序统计量 X ( 1 ) X_{(1)} X(1)的分布函数与期望.
Solution: 设 Y = X ( 1 ) Y=X_{(1)} Y=X(1), 当 y ∈ ( 0 , 1 ) y \in(0,1) y∈(0,1) 时, P { Y ≥ y } = P ( min { X 1 , X 2 , X 3 } ≥ y ) = P 3 { X 1 ≥ y } = ( 1 − y ) 3 P\{Y \geq y\}=P\left(\min \left\{X_{1}, X_{2}, X_{3}\right\} \geq y\right)=P^{3}\left\{X_{1} \geq y\right\}=(1-y)^{3} P{ Y≥y}=P(min{ X1,X2,X3}≥y)=P3{ X1≥y}=(1−y)3 所以分布函数是
F ( y ) = { 0 , y < 0 , 1 − ( 1 − y ) 3 , 0 ≤ y < 1 , 1 , y ≥ 1. F(y)=\left\{\begin{array}{lc}0, & y<0, \\ 1-(1-y)^{3}, & 0 \leq y<1, \\ 1, & y \geq 1 .\end{array}\right. F(y)=⎩⎨⎧0,1−(1−y)3,1,y<0,0≤y<1,y≥1. 这恰好是 Beta ( 1 , 3 ) \operatorname{Beta}(1,3) Beta(1,3)的分布函数. E Y = ∫ 0 1 y d F ( y ) = 1 ⋅ F ( 1 ) − ∫ 0 1 [ 1 − ( 1 − y ) 3 ] d y = 1 4 E Y=\int_{0}^{1} y d F(y)=1 \cdot F(1)-\int_{0}^{1}\left[1-(1-y)^{3}\right] d y=\frac{1}{4} EY=∫01ydF(y)=1⋅F(1)−∫01[1−(1−y)3]dy=41
八、(30分) 有来自 X ∼ f ( x ) = { θ , 0 ≤ x < 1 1 − θ , 1 ≤ x < 2 , 0 , otherwise X \sim f(x)=\left\{\begin{array}{cl}\theta, & 0 \leq x<1 \\ 1-\theta, & 1 \leq x<2, \\ 0, & \text { otherwise }\end{array}\right. X∼f(x)=⎩⎨⎧θ,1−θ,0,0≤x<11≤x<2, otherwise 的 n n n 个简单随机样本, 求
(1)(15分) θ \theta θ 的矩估计;
(2)(15分) θ \theta θ 的最大似然估计, 已知 m = ∑ i = 1 n I [ X i < 1 ] m=\sum_{i=1}^{n} I\left[X_{i}<1\right] m=∑i=1nI[Xi<1].
Solution: (1) E X = ∫ 0 1 x θ d x + ∫ 1 2 x ( 1 − θ ) d x = 3 2 − θ E X=\int_{0}^{1} x \theta d x+\int_{1}^{2} x(1-\theta) d x=\frac{3}{2}-\theta EX=∫01xθdx+∫12x(1−θ)dx=23−θ, 因此 θ ^ 1 = 3 2 − X ˉ . \hat{\theta}_{1}=\frac{3}{2}-\bar{X}. θ^1=23−Xˉ.(2) 似然函数 L ( x 1 , … , x n ; θ ) = θ m ( 1 − θ ) n − m , L\left(x_{1}, \ldots, x_{n} ; \theta\right)=\theta^{m}(1-\theta)^{n-m}, L(x1,…,xn;θ)=θm(1−θ)n−m,
ln L = m ln θ + ( n − m ) ln ( 1 − θ ) \ln L=m \ln \theta+(n-m) \ln(1-\theta) lnL=mlnθ+(n−m)ln(1−θ), 对 θ \theta θ 求偏导, 得 ∂ ln L ∂ θ = m θ − n − m 1 − θ = l e t 0 , \frac{\partial \ln L}{\partial \theta}=\frac{m}{\theta}-\frac{n-m}{1-\theta} \stackrel{l e t}{=} 0, ∂θ∂lnL=θm−1−θn−m=let0,解得 θ ^ 2 = m n \hat{\theta}_{2}=\frac{m}{n} θ^2=nm.
边栏推荐
- Abstract classes and interfaces
- TYUT太原理工大学2022软工导论大题汇总
- Quickly generate illustrations
- Cloud native trend in 2022
- MySQL limit x, -1 doesn't work, -1 does not work, and an error is reported
- 六种集合的遍历方式总结(List Set Map Queue Deque Stack)
- How to ensure data consistency between MySQL and redis?
- TYUT太原理工大学2022数据库之关系代数小题
- C language to achieve mine sweeping game (full version)
- 165. Compare version number - string
猜你喜欢
3.C语言用代数余子式计算行列式
3. Number guessing game
Arduino+ds18b20 temperature sensor (buzzer alarm) +lcd1602 display (IIC drive)
String class
TYUT太原理工大学2022软工导论大题汇总
Experience summary of autumn recruitment of state-owned enterprises
Tyut Taiyuan University of technology 2022 "Mao Gai" must be recited
继承和多态(下)
2.C语言矩阵乘法
The overseas sales of Xiaomi mobile phones are nearly 140million, which may explain why Xiaomi ov doesn't need Hongmeng
随机推荐
5.MSDN的下载和使用
System design learning (III) design Amazon's sales rank by category feature
Ten minutes to thoroughly master cache breakdown, cache penetration, cache avalanche
凡人修仙学指针-2
The overseas sales of Xiaomi mobile phones are nearly 140million, which may explain why Xiaomi ov doesn't need Hongmeng
6. Function recursion
Rich Shenzhen people and renting Shenzhen people
Floating point comparison, CMP, tabulation ideas
20220211-CTF-MISC-006-pure_ Color (use of stegsolve tool) -007 Aesop_ Secret (AES decryption)
Set container
Small exercise of library management system
4.分支语句和循环语句
List set map queue deque stack
图书管理系统小练习
Cloud native trend in 2022
Decomposition relation model of the 2022 database of tyut Taiyuan University of Technology
系统设计学习(三)Design Amazon‘s sales rank by category feature
Comparison between FileInputStream and bufferedinputstream
MPLS experiment
View UI plus released version 1.3.1 to enhance the experience of typescript