如果你也在 怎样代写抽样调查Survey sampling 这个学科遇到相关的难题,请随时右上角联系我们的24/7代写客服。抽样调查Survey sampling是数学工程这一广泛新兴领域中的一个自然组成部分。例如,我们可以断言,数学工程之于今天的数学系,就像数学物理之于一个世纪以前的数学系一样;毫不夸张地说,数学在诸如语音和图像处理、信息理论和生物医学工程等工程学科中的基本影响。
抽样调查Survey sampling是主流统计的边缘。这里的特殊之处在于,我们有一个具有某些特征的有形物体集合,我们打算通过抓住其中一些物体并试图对那些未被触及的物体进行推断来窥探它们。这种推论传统上是基于一种概率论,这种概率论被用来探索观察到的事物与未观察到的事物之间的可能联系。这种概率不被认为是在统计学中,涵盖其他领域,以表征我们感兴趣的变量的单个值之间的相互关系。但这是由调查抽样调查人员通过任意指定的一种技术从具有预先分配概率的对象群体中选择样本而创建的。
avatest™帮您通过考试
avatest™的各个学科专家已帮了学生顺利通过达上千场考试。我们保证您快速准时完成各时长和类型的考试,包括in class、take home、online、proctor。写手整理各样的资源来或按照您学校的资料教您,创造模拟试题,提供所有的问题例子,以保证您在真实考试中取得的通过率是85%以上。如果您有即将到来的每周、季考、期中或期末考试,我们都能帮助您!
在不断发展的过程中,avatest™如今已经成长为论文代写,留学生作业代写服务行业的翘楚和国际领先的教育集团。全体成员以诚信为圆心,以专业为半径,以贴心的服务时刻陪伴着您, 用专业的力量帮助国外学子取得学业上的成功。
•最快12小时交付
•200+ 英语母语导师
•70分以下全额退款
统计代写|抽样调查代考Survey sampling代写|Unbiased Estimation of $Y$
Let $E_1, V_1$ denote expectation variance operators for the sampling design in the first stage and $E_L, V_L$ those in the later stages. Let $R_i$ be independent variables satisfying
(a) $E_L\left(R_i\right)=Y_i$,
(b) $V_L\left(R_i\right)=V_i$ or
(c) $V_L\left(R_i\right)=V_{s i}$
and let there exist (b) $)^{\prime}$ random variables $v_i$ such that $E_L\left(v_i\right)=$ $V_i$ or (c)’ random variables $v_{s i}$ such that $E_L\left(v_{s i}\right)=V_{s i}$.
Let $E=E_1 E_L=E_L E_1$ be the overall expectation and $V=$ $E_1 V_L+V_1 E_L=E_L V_1+V_L E_1$ the overall variance operators. CHAUDHURI, ADHIKARI and DIHIDAR (2000a, 2000b) have illustrated how these commutativity assumptions may be valid in the context of survey sampling.
Let
$$
\begin{aligned}
t_b & =\sum b_{s i} I_{s i} Y_i, \
M_1\left(t_b\right) & =E_1\left(t_b-Y\right)^2=\sum \sum d_{i j} y_i y_j, \
d_{i j} & =E_1\left(b_{s i} I_{s i}-1\right)\left(b_{s j} I_{s j}-1\right),
\end{aligned}
$$
$d_{s i j}$ be constants free of $Y$ such that
$$
E_1\left(d_{s i j} I_{s i j}\right)=d_{i j} \forall_{i, j} \text { in } U .
$$
Let $w_i$ ‘s be certain non-zero constants. Then, one gets
$$
\begin{aligned}
M_1\left(t_b\right)= & -\sum \sum_{i<j} d_{i j} w_i w_j\left(\frac{Y_i}{w_i}-\frac{Y_j}{w_j}\right)^2 \
& +\sum \beta_i \frac{Y_i^2}{w_i} \text { when } \beta_i=\sum_{j=1}^N d_{i j} w_j .
\end{aligned}
$$
统计代写|抽样调查代考Survey sampling代写|PPSWR Sampling of First-Stage Units
First, from DES RAJ (1968) we note the following. Suppose a PPSWR sample of fsus is chosen in $n$ draws from $U$ using normed size measures $P_i\left(0<P_i<i, \Sigma P_i=1\right)$. Writing $y_r\left(p_r\right)$ for the $Y_i\left(p_i\right)$ value for the unit chosen on the $r$ th draw, $(r=$ $1, \ldots, n)$ the HANSEN-HURWITZ estimator
$$
t_{H H}=\frac{1}{n} \sum_{n=1}^n \frac{y_r}{p_r}
$$
might be used to estimate $Y$ because $E_p\left(t_{H H}\right)=Y$ if $Y_i$ could be ascertained. But since $Y_i$ ‘s are not ascertainable, suppose that each time an fsu $i$ appears in one of the $n$ independent draws by PPSWR method, an independent subsample of elements is selected in subsequent stages in such a manner that estimators $\hat{y}r$ for $y_r$ are available such that $E_L\left(\hat{y}_r\right)=y_r$ and $V_L\left(\hat{y}_r\right)=\sigma_r^2$ with uncorrelated $y_1, y_2, \ldots, y_n$. Then, DAS RAJ’s (1968) proposed estimator for $Y$ is $$ e_H=\frac{1}{n} \sum{r=1}^n \frac{\hat{y}r}{p_r} $$ for which the variance is $$ \begin{aligned} V\left(e_H\right) & =V_p\left(t{H H}\right)+E_p\left[\frac{1}{n^2} \sum_{r=1}^n \frac{\sigma_r^2}{p_r^2}\right] \
& =\frac{1}{n} \sum P_i\left(\frac{Y_i}{P_i}-Y\right)^2+\frac{1}{n} \sum_1^N \frac{\sigma_i^2}{P_i} \
& =V_H, \text { say. }
\end{aligned}
$$
It follows that
$$
\begin{aligned}
& v_H=\frac{1}{2 n^2(n-1)} \sum_{\substack{r=1 r^{\prime}=1 \
r \neq r^{\prime}}}^n\left(\frac{\hat{y}{r^{\prime}}}{p{r^{\prime}}}-\frac{\hat{y}r}{p_r}\right)^2 \ & r \neq r^{\prime} \ & \end{aligned} $$ is an unbiased estimator for $V_H$ because $$ \begin{aligned} E_l\left(v_H\right) & =\frac{1}{2 n^2(n-1)} \sum{r \neq r^{\prime}}\left[\frac{y_r^2}{p_r^2}+\frac{y_{r^{\prime}}^2}{p_{r^{\prime}}^2}+\frac{\sigma_r^2}{p_r^2}+\frac{\sigma_{r^{\prime}}^2}{p_{r^{\prime}}^2}-2 \frac{y_r}{p_r} \frac{y_{r^{\prime}}}{p_{r^{\prime}}}\right] \
E v_H & =E_p E_L\left(v_H\right)=\frac{1}{n}\left(\sum \frac{Y_i^2}{P_i}-Y^2\right)+\frac{1}{n} \sum \frac{\sigma_i^2}{P_i} \
& =\frac{1}{n} \sum P_i\left(\frac{Y_i}{P_i}-Y\right)^2+\frac{1}{n} \sum \frac{\sigma_i^2}{P_i}=V\left(e_H\right) .
\end{aligned}
$$
抽样调查代写
统计代写|抽样调查代考Survey sampling代写|Unbiased Estimation of $Y$
设$E_1, V_1$为第一阶段抽样设计的期望方差算子,$E_L, V_L$为后期抽样设计的期望方差算子。设$R_i$为自变量满足
(a) $E_L\left(R_i\right)=Y_i$;
(b) $V_L\left(R_i\right)=V_i$或
(c) $V_L\left(R_i\right)=V_{s i}$
假设存在(b) $)^{\prime}$随机变量$v_i$使得$E_L\left(v_i\right)=$$V_i$或(c)’随机变量$v_{s i}$使得$E_L\left(v_{s i}\right)=V_{s i}$。
设$E=E_1 E_L=E_L E_1$为总期望,$V=$$E_1 V_L+V_1 E_L=E_L V_1+V_L E_1$为总方差算子。CHAUDHURI, ADHIKARI和DIHIDAR (2000a, 2000b)已经说明了这些交换性假设如何在调查抽样的背景下有效。
让
$$
\begin{aligned}
t_b & =\sum b_{s i} I_{s i} Y_i, \
M_1\left(t_b\right) & =E_1\left(t_b-Y\right)^2=\sum \sum d_{i j} y_i y_j, \
d_{i j} & =E_1\left(b_{s i} I_{s i}-1\right)\left(b_{s j} I_{s j}-1\right),
\end{aligned}
$$
$d_{s i j}$ 使用不含$Y$的常量
$$
E_1\left(d_{s i j} I_{s i j}\right)=d_{i j} \forall_{i, j} \text { in } U .
$$
设$w_i$是非零常数。然后,我们得到
$$
\begin{aligned}
M_1\left(t_b\right)= & -\sum \sum_{i<j} d_{i j} w_i w_j\left(\frac{Y_i}{w_i}-\frac{Y_j}{w_j}\right)^2 \
& +\sum \beta_i \frac{Y_i^2}{w_i} \text { when } \beta_i=\sum_{j=1}^N d_{i j} w_j .
\end{aligned}
$$
统计代写|抽样调查代考Survey sampling代写|PPSWR Sampling of First-Stage Units
首先,从DES RAJ(1968)中我们注意到以下几点。假设使用规范尺寸测量$P_i\left(0<P_i<i, \Sigma P_i=1\right)$从$U$中选择fsus的PPSWR样本$n$。写入$y_r\left(p_r\right)$为$r$次抽奖中选择的单位的$Y_i\left(p_i\right)$值,$(r=$$1, \ldots, n)$为HANSEN-HURWITZ估计器
$$
t_{H H}=\frac{1}{n} \sum_{n=1}^n \frac{y_r}{p_r}
$$
可以用来估计$Y$,因为$E_p\left(t_{H H}\right)=Y$如果$Y_i$可以确定。但是,由于$Y_i$是不可确定的,假设每次fsu $i$出现在PPSWR方法的$n$独立抽取中,在随后的阶段以这样的方式选择元素的独立子样本,即$y_r$的估计量$\hat{y}r$可用,从而$E_L\left(\hat{y}r\right)=y_r$和$V_L\left(\hat{y}_r\right)=\sigma_r^2$与不相关的$y_1, y_2, \ldots, y_n$。然后,DAS RAJ(1968)提出$Y$的估计量为$$ e_H=\frac{1}{n} \sum{r=1}^n \frac{\hat{y}r}{p_r} $$,其方差为$$ \begin{aligned} V\left(e_H\right) & =V_p\left(t{H H}\right)+E_p\left[\frac{1}{n^2} \sum{r=1}^n \frac{\sigma_r^2}{p_r^2}\right] \
& =\frac{1}{n} \sum P_i\left(\frac{Y_i}{P_i}-Y\right)^2+\frac{1}{n} \sum_1^N \frac{\sigma_i^2}{P_i} \
& =V_H, \text { say. }
\end{aligned}
$$
由此得出
$$
\begin{aligned}
& v_H=\frac{1}{2 n^2(n-1)} \sum_{\substack{r=1 r^{\prime}=1 \
r \neq r^{\prime}}}^n\left(\frac{\hat{y}{r^{\prime}}}{p{r^{\prime}}}-\frac{\hat{y}r}{p_r}\right)^2 \ & r \neq r^{\prime} \ & \end{aligned} $$是$V_H$的无偏估计量,因为 $$ \begin{aligned} E_l\left(v_H\right) & =\frac{1}{2 n^2(n-1)} \sum{r \neq r^{\prime}}\left[\frac{y_r^2}{p_r^2}+\frac{y_{r^{\prime}}^2}{p_{r^{\prime}}^2}+\frac{\sigma_r^2}{p_r^2}+\frac{\sigma_{r^{\prime}}^2}{p_{r^{\prime}}^2}-2 \frac{y_r}{p_r} \frac{y_{r^{\prime}}}{p_{r^{\prime}}}\right] \
E v_H & =E_p E_L\left(v_H\right)=\frac{1}{n}\left(\sum \frac{Y_i^2}{P_i}-Y^2\right)+\frac{1}{n} \sum \frac{\sigma_i^2}{P_i} \
& =\frac{1}{n} \sum P_i\left(\frac{Y_i}{P_i}-Y\right)^2+\frac{1}{n} \sum \frac{\sigma_i^2}{P_i}=V\left(e_H\right) .
\end{aligned}
$$
统计代写|抽样调查代考Survey sampling代写 请认准exambang™. exambang™为您的留学生涯保驾护航。
在当今世界,学生正面临着越来越多的期待,他们需要在学术上表现优异,所以压力巨大。
avatest.org 为您提供可靠及专业的论文代写服务以便帮助您完成您学术上的需求,让您重新掌握您的人生。我们将尽力给您提供完美的论文,并且保证质量以及准时交稿。除了承诺的奉献精神,我们的专业写手、研究人员和校对员都经过非常严格的招聘流程。所有写手都必须证明自己的分析和沟通能力以及英文水平,并通过由我们的资深研究人员和校对员组织的面试。
其中代写论文大多数都能达到A,B 的成绩, 从而实现了零失败的目标。
这足以证明我们的实力。选择我们绝对不会让您后悔,选择我们是您最明智的选择!