概率论与数理统计浙大第五版 第七章 部分习题+R代码

习题七

1、

$$\begin{gathered} {\mu }_1=E(X)=\mu \\ =\frac{1}{n}{\sum }_{i=1}^n{x}_i \\ =\frac{1}{8}(74.001+74.005+74.003+74.001+74.000+73.998+74.006+74.002)=74.002 \end{gathered}$$

$$\begin{gathered} {\sigma }^2=\frac{1}{n}{\sum }_{i=1}^n(x_i-\mu {)}^2 \\ =\frac{1}{8}[(\mu -74.001{)}^2+(\mu -74.005{)}^2+(\mu -74.003{)}^2+(\mu -74.001{)}^2+(\mu -74.000{)}^2+(\mu -73.998{)}^2+(\mu -74.006{)}^2+(\mu -74.002{)}^2] \\ =6\ast 10^{-6} \end{gathered}$$

样本方差和总体方差的关系得到

$S^2=\frac{n}{n-1}{\sigma }^2=6.86\ast 10^{-6}$

x<-c(74.001,74.005,74.003,74.001,74.000,73.998,74.006,74.002)
mean(x)                          # \mu
sum((x-mean(x))^2)/length(x)     # \sigma^2
var(x)                           # S^2

6、

由题意可得$X\sim B(10,p)P(X=k)=C_{10}^k{p}^k(1-p{)}^{10-k}$

似然函数为$L(p)={\prod }_{i=1}^{100}{C}_{10}^k{p}^k(1-p{)}^{1-k}$

$lnL(p)=({\sum }_{i=1}^{100}{x}_i)lnp+(1000-{\sum }_{i=1}^{100}x+i)ln(1-p)+{\sum }_{i=1}^{100}ln{C}_{10}^{x_i}$

$\frac{dlnL}{dp}=\frac{{\sum }_{i=1}^{100}x}{p}-\frac{1}{1-p}(1000-{\sum }_{i=1}^{100}{x}_i)=0$

解得：$\hat{P}=\frac{{\sum }_{i=1}^n{x}_i}{n^2}=\frac{\bar{X}}{n}=\frac{499}{1000}=0.499$

由此可得

当总体$X$服从二项分布$X\sim B(n,p)$时，参数p的极大似然估计为$\hat{P}=\frac{\bar{X}}{n}$

sum(0*0,1*1,6*2,3*7,4*23,5*26,6*21,7*12,8*3,9*1,10*0)/1000

16、

（1）

根据题意$\sigma$已知，求$\mu$的置信水平为0.95的置信区间

P { − Z α 2 < X ˉ − μ σ / n < Z α 2 } = 1 − α P\{-Z_{\frac{\alpha}{2}}<\frac{\bar X-\mu}{\sigma/\sqrt{n}}<Z_{\frac{\alpha}{2}}\}=1-\alpha P{−Z2α​​<σ/n ​Xˉ−μ​<Z2α​​}=1−α

解得：$(\bar{X}-\frac{\sigma }{\sqrt{n}}{Z}_{\frac{\alpha }{2}},\bar{X}+\frac{\sigma }{\sqrt{n}}{Z}_{\frac{\alpha }{2}})$将$\sigma =0.6,1-\alpha =0.95,Z_{\frac{\alpha }{2}}=1.96,\bar{X}=6$代入得置信区间为$(5.608,6.392)$

x<-c(6.0,5.7,5.8,6.5,7.0,6.3,5.6,6.1,5.0)
m<-mean(x)    # \bar X
sigma<-0.6    # \sigma
n<-length(x)
alpha<-0.05
m+sigma/sqrt(n)*qnorm(1-alpha/2)
m-sigma/sqrt(n)*qnorm(1-alpha/2)

（2）

$\sigma$未知，求$\mu$的置信水平为0.95的置信区间

P { − t α 2 ( n − 1 ) < X ˉ − μ S / n < t α 2 ( n − 1 ) } = 1 − α P\{-t_{\frac{\alpha}{2}}(n-1)<\frac{\bar X-\mu}{S/\sqrt{n}}<t_{\frac{\alpha}{2}}(n-1)\}=1-\alpha P{−t2α​​(n−1)<S/n ​Xˉ−μ​<t2α​​(n−1)}=1−α

$(\bar{X}-\frac{S}{\sqrt{n}}{t}_{\frac{\alpha }{2}}(n-1),\bar{X}+\frac{S}{\sqrt{n}}{t}_{\frac{\alpha }{2}}(n-1))$

代入数据得置信区间为（5.558，6.442）

x<-c(6.0,5.7,5.8,6.5,7.0,6.3,5.6,6.1,5.0)
m<-mean(x)    # \bar X
S<-sd(x)      # S
n<-length(x)
alpha<-0.05
m+S/sqrt(n)*qt(1-alpha/2,n-1)
m-S/sqrt(n)*qt(1-alpha/2,n-1)

18、

$\mu$未知，求$\sigma$的置信水平为0.95的置信区间

P { χ 1 − α 2 2 ( n − 1 ) < ( n − 1 ) S 2 σ 2 < χ α 2 2 ( n − 1 ) } = 1 − α P\{ \chi^2_{1-\frac{\alpha}{2}}(n-1)<\frac{(n-1)S^2}{\sigma^2}< \chi^2_{\frac{\alpha}{2}}(n-1)\}=1-\alpha P{χ1−2α​2​(n−1)<σ2(n−1)S2​<χ2α​2​(n−1)}=1−α

解得：$(\frac{(n-1)S^2}{{\chi }_{\frac{\alpha }{2}}^2(n-1)},\frac{(n-1)S^2}{{\chi }_{1-\frac{\alpha }{2}}^2(n-1)})$

代入数据得：$(7.4,21.1)$

s<-11
alpha<-0.05
n<-9
df<-n-1
sqrt(df*s^2/qchisq(1-alpha/2,df))
sqrt(df*s^2/qchisq(alpha/2,df))

21、

${\mu }_1,{\mu }_2,\sigma$均未知，求${\mu }_1-{\mu }_2$置信度为0.95的置信区间

直接套公式，置信区间为$(\bar{X}-\bar{Y}-t_{\frac{\alpha }{2}}(n_1+n_2-2)S_w\sqrt{\frac{1}{n_1}+\frac{1}{n_2}},\bar{X}-\bar{Y}+t_{\frac{\alpha }{2}}(n_1+n_2-2)S_w\sqrt{\frac{1}{n_1}+\frac{1}{n_2}})$

代入数据得：$(-0.002，0.006)$

x1<-c(0.143,0.142,0.143,0.137)
x2<-c(0.140,0.142,0.136,0.138,0.140)
m1<-mean(x1)
m2<-mean(x2)
alpha=0.05
n1<-length(x1)
n2<-length(x2)
sw<-sqrt(((n1-1)*var(x1)+(n2-1)*var(x2))/(n1+n2-2))
m1-m2-qt(1-alpha/2,n1+n2-2)*sw*(sqrt(1/n1+1/n2))
m1-m2+qt(1-alpha/2,n1+n2-2)*sw*(sqrt(1/n1+1/n2))

23、

${\mu }_1,{\mu }_2$均未知，求$\frac{{\sigma }_A^2}{{\sigma }_B^2}$置信度为0.95的置信区间

置信区间为

$(\frac{S_1^2}{S_2^2}\frac{1}{F_{\frac{\alpha }{2}}(n_1-1,n_2-1)},\frac{S_1^2}{S_2^2}\frac{1}{F_{1-\frac{\alpha }{2}}(n_1-1,n_2-1)})$

代入数据解得：$(0.222,3.601)$

sa=0.5419
sb=0.6065
alpha=0.05
n=10
del=sa/sb
del/qf(1-alpha/2,n-1,n-1)
del/qf(alpha/2,n-1,n-1)

25、

（1）

依题意求$\sigma$未知$\mu$的单侧置信上限

$\bar{\mu }=\bar{X}+\frac{S}{\sqrt{n}{t}_{\alpha }(n-1)}$

代入数据解得：$(-\infty ,6.108)$

x<-c(6.0,5.7,5.8,6.5,7.0,6.3,5.6,6.1,5.0)
m<-mean(x)    # \bar X
sigma<-0.6    # \sigma
n<-length(x)
alpha<-0.05
m+sigma/sqrt(n)/qt(1-alpha,n-1)

（2）

依题意求$\sigma$未知${\mu }_1-{\mu }_2$的单侧置信下限

$\underline{{\mu }_1-{\mu }_2}=\bar{X}-\bar{Y}-t_{\alpha }(n_1+n_2-2)S_w\sqrt{\frac{1}{n_1}+\frac{1}{n_2}}$

代入数据解得：$(-0.001,+\infty )$

x1<-c(0.143,0.142,0.143,0.137)
x2<-c(0.140,0.142,0.136,0.138,0.140)
m1<-mean(x1)
m2<-mean(x2)
alpha=0.05
n1<-length(x1)
n2<-length(x2)
sw<-sqrt(((n1-1)*var(x1)+(n2-1)*var(x2))/(n1+n2-2))
m1-m2-qt(1-alpha,n1+n2-2)*sw*(sqrt(1/n1+1/n2))

（3）

依题意求${\mu }_1,\mu 2$未知$\frac{{\sigma }_1^2}{{\sigma }_2^2}$的单侧置信上限

$\overline{\frac{{\sigma }_1^2}{{\sigma }_2^2}}=\frac{S_1^2}{S_2^2}\frac{1}{F_{1-\alpha }(n_1-1,n_2-1)}$

代入数据解得：$(-\infty ,0.281)$

sa=0.5419
sb=0.6065
alpha=0.05
n=10
del=sa/sb
del/qf(1-alpha,n-1,n-1)