【学习笔记】数理统计习题五

Q1: Let $X_1,\dots ,X_n$ be a sample from density
$$f(x;\sigma )=\frac{1}{2\sigma }{e}^{-|x|/\sigma },$$where $\sigma >0$. Find the maximum likelihood estimator for $\sigma$.

Solution： 似然函数为：
$$L(\sigma )=\prod _{i=1}^{n}f(x_i)=\prod _{i=1}^n(\frac{1}{2\sigma }{e}^{-|x_i|/\sigma })=(2\sigma {)}^{-n}exp(-\frac{1}{\sigma }\sum _{i=1}^n|x_i|)$$于是有
$$\ell (\sigma )=lnL(\sigma )=-nln(2\sigma )-\frac{1}{\sigma }\sum _{i=1}^n|x_i|$$令
$$\frac{\partial }{\partial \sigma }\ell (\sigma )=-\frac{n}{\sigma }+\frac{1}{{\sigma }^2}\sum _{i=1}^n|x_i|=0$$可解得
$$\hat{\sigma }=\frac{\sum _{i=1}^n|x_i|}{n}$$因此，我们可以得到$\sigma$的极大似然估计值${\hat{\sigma }}_{MLE}=\frac{1}{n}{\sum }_{i=1}^n|X_i|$

Q2: Let $X_1,\dots ,X_n$ be a sample from $\mathbb{U}[\theta ,\theta +1]$, where $\theta \in \mathbb{R}$. Prove that the maximum likelihood estimator (MLE) for $\theta$ is not unique, and find out all the MLEs.

Solution： 随机变量$X_1,X_2,\cdots ,X_n$服从均匀分布$\mathbb{U}[\theta ,\theta +1]$，则其概率密度为：
$$f(x;\theta )=\{\begin{array}{ll}1& \theta \le x\le \theta +1\\ 0& 其他\end{array}$$似然函数为：
$$L(\theta )=\prod _{i=1}^{n}f(x_i)=\prod _{i=1}^n$$