# 统计代写|应用线性模型代写Applied Linear Models代考|STAT704

## 统计代写|应用线性模型代写Applied Linear Models代考|Estimation under the null hypothesis

When considering the hypothesis $H: \quad \mathbf{K}^{\prime} \mathbf{b}=\mathbf{m}$ it is natural to ask, “What is the estimator of $\mathbf{b}$ under the null hypothesis?” This might be especially pertinent following non-rejection of the hypothesis by the preceding $F$-test. The desired estimator, $\tilde{b}$ say, is readily obtainable using constrained least squares. Thus $\tilde{\mathbf{b}}$ is derived so as to minimize $(\mathbf{y}-\mathbf{X} \tilde{\mathbf{b}})^{\prime}(\mathbf{y}-\mathbf{X} \tilde{\mathbf{b}})$ subject to the constraint $\mathbf{K}^{\prime} \mathbf{b}=\mathbf{m}$.

With $2 \theta^{\prime}$ as a vector of Lagrange multipliers we minimize
$$(\mathbf{y}-\mathbf{X} \tilde{b})^{\prime}(\mathbf{y}-\mathbf{X} \tilde{\mathbf{b}})+2 \mathbf{\theta}^{\prime}\left(\mathbf{K}^{\prime} \tilde{\mathbf{b}}-\mathbf{m}\right)$$
with respect to the elements of $\overrightarrow{\mathbf{b}}$ and $\boldsymbol{\theta}$. Differentiation with respect to these elements leads to the equations
with the other terms vanishing because $\mathbf{X}^{\prime}(\mathbf{y}-\mathbf{X} \hat{\mathbf{b}})=\mathbf{0}$.

## 统计代写|应用线性模型代写Applied Linear Models代考|Reduced models

We now consider, in turn, the effect on the model $\mathbf{y}=\mathbf{X b}+\mathbf{e}$ of the hypotheses $\mathbf{K}^{\prime} \mathbf{b}=\mathbf{m}, \mathbf{K}^{\prime} \mathbf{b}=\mathbf{0}$ and $\mathbf{b}q=\mathbf{0}$. (i) $\mathbf{K}^{\prime} \mathbf{b}=\mathbf{m}$. In estimating $\mathbf{b}$ subject to $\mathbf{K}^{\prime} \mathbf{b}=\mathbf{m}$ it could be said that we are dealing with a model $\mathbf{y}=\mathbf{X b}+\mathbf{e}$ on which has been imposed the limitation $\mathbf{K}^{\prime} \mathbf{b}=\mathbf{m}$. We refer to the model that we start with, $\mathbf{y}=\mathbf{X b}+\mathbf{e}$ without the limitation, as the full model; and the model with the limitation imposed, $\mathbf{y}=\mathbf{X b}+\mathbf{e}$ with $\mathbf{K}^{\prime} \mathbf{b}=\mathbf{m}$, is called the reduced model. For example, if the full model is $$y_i=b_0+b_1 x{i 1}+b_2 x_{i 2}+b_3 x_{i 3}+e_i$$
and the hypothesis is $H: b_1=b_2$, the reduced model is
$$y_i=b_0+b_1\left(x_{i 1}+x_{i 2}\right)+b_3 x_{i 3}+e_i .$$
The meaning of $Q$ and of SSE $+Q$ is now investigated in terms of sums of squares associated with the full and reduced models. To aid description we introduce the terms reduction(full) and residual(full) for the reduction and residual sums of squares after fitting the full model:
reduction(full) $=$ SSR $\quad$ and $\quad$ residual(full $)=$ SSE.
Similarly
$$\mathrm{SSE}+Q=\text { residual(reduced), }$$
as established in (105). Hence
\begin{aligned} Q &=\mathrm{SSE}+Q-\mathrm{SSE} \ &=\text { residual(reduced })-\text { residual(full) } \end{aligned} and also
\begin{aligned} Q &=\mathbf{y}^{\prime} \mathbf{y}-\mathrm{SSE}-\left[\mathbf{y}^{\prime} \mathbf{y}-(\mathrm{SSE}+Q)\right] \ &=\mathrm{SSR}-\left[\mathbf{y}^{\prime} \mathbf{y}-(\mathrm{SSE}+Q)\right] \ &=\text { reduction(full })-\left[\mathbf{y}^{\prime} \mathbf{y}-(\mathrm{SSE}+Q)\right] \end{aligned}

## 统计代写|应用线性模型代写Applied Linear Models代考|Estimation under the null hypothesis

$$(\mathbf{y}-\mathbf{X} \tilde{b})^{\prime}(\mathbf{y}-\mathbf{X} \tilde{\mathbf{b}})+2 \theta^{\prime}\left(\mathbf{K}^{\prime} \tilde{\mathbf{b}}-\mathbf{m}\right)$$

## 统计代写|应用线性模型代写Applied Linear Models代考|Reduced models

$$y_i=b_0+b_1 x i 1+b_2 x_{i 2}+b_3 x_{i 3}+e_i$$

$$y_i=b_0+b_1\left(x_{i 1}+x_{i 2}\right)+b_3 x_{i 3}+e_i .$$

$$\mathrm{SSE}+Q=\text { residual(reduced) }$$

$$Q=\mathrm{SSE}+Q-\mathrm{SSE} \quad=\text { residual(reduced })-\operatorname{residual}(\text { full })$$

$$\left.Q=\mathbf{y}^{\prime} \mathbf{y}-\operatorname{SSE}-\left[\mathbf{y}^{\prime} \mathbf{y}-(\mathrm{SSE}+Q)\right] \quad=\operatorname{SSR}-\left[\mathbf{y}^{\prime} \mathbf{y}-(\mathrm{SSE}+Q)\right]=\text { reduction(full }\right)-\left[\mathbf{y}^{\prime} \mathbf{y}\right.$$

myassignments-help数学代考价格说明

1、客户需提供物理代考的网址，相关账户，以及课程名称，Textbook等相关资料~客服会根据作业数量和持续时间给您定价~使收费透明，让您清楚的知道您的钱花在什么地方。

2、数学代写一般每篇报价约为600—1000rmb，费用根据持续时间、周作业量、成绩要求有所浮动(持续时间越长约便宜、周作业量越多约贵、成绩要求越高越贵)，报价后价格觉得合适，可以先付一周的款，我们帮你试做，满意后再继续，遇到Fail全额退款。

3、myassignments-help公司所有MATH作业代写服务支持付半款，全款，周付款，周付款一方面方便大家查阅自己的分数，一方面也方便大家资金周转，注意:每周固定周一时先预付下周的定金，不付定金不予继续做。物理代写一次性付清打9.5折。

Math作业代写、数学代写常见问题

myassignments-help擅长领域包含但不是全部: