assignmentutor-lab™ 为您的留学生涯保驾护航 在代写时间序列分析Time-Series Analysis方面已经树立了自己的口碑, 保证靠谱, 高质且原创的统计Statistics代写服务。我们的专家在代写时间序列分析Time-Series Analysis代写方面经验极为丰富，各种代写时间序列分析Time-Series Analysis相关的作业也就用不着说。

• Statistical Inference 统计推断
• Statistical Computing 统计计算
• (Generalized) Linear Models 广义线性模型
• Statistical Machine Learning 统计机器学习
• Longitudinal Data Analysis 纵向数据分析
• Foundations of Data Science 数据科学基础

## 统计代写|时间序列分析代写Time-Series Analysis代考|Forecasting Global Temperatures Using Exponential

In Example 4.3, an ARIMA( $0,1,3)$ process without drift was fitted to monthly global temperatures, and in Example $7.2$ this model was used to provide forecasts out to 2020. As $\hat{\theta}2$ and $\hat{\theta}_3$, although significant, are both small when compared to $\hat{\theta}_1$, an $\operatorname{ARIMA}(0,1,1)$ process should provide a decent fit to the series, and indeed it does, with $\hat{\theta}=0.55$ and a root mean square error (RMSE) of $0.1255$ [compared with $0.1236$ for $\operatorname{ARIMA}(0,1,3)$ ]. From the equivalence of simple exponential smoothing and the ARIMA(0,1,1), we would expect the former model to produce a similar fit and forecasts for a smoothing parameter of $\alpha=0.45$. Fitting the series by simple exponential smoothing and estimating $\alpha$ does indeed lead to this value for the smoothing parameter, an RMSE of $0.1257$, and forecasts given by $f{T, h}=z_T=0.581$. These should be compared to the $\operatorname{ARIMA}(0,1,3)$ forecasts obtained in Example 7.2, which, for $h>2$, are equal to $0.621$.

Acknowledging the possibility of a linear trend in global temperatures would require the use of either double exponential smoothing or Holt-Winters. The former estimates the single smoothing parameter to be $\gamma=0.196$, accompanied by an RMSE of $0.1319$. Interestingly, double exponential smoothing gives $z_T=0.569$ and $\tau_T=-0.014$, so that, using (9.14), forecasts will contain a negatively sloped, albeit small, linear trend. Holt-Winters estimates the smoothing parameters as $\alpha=0.45$ and $\beta=0$, which implies that the trend component is a constant, so that $\tau_t=\tau_{t-1}=\cdots=\tau$, a value that is estimated by $x_2-x_1=0.0005$. The Holt-Winters forecasts thus include a small positive linear trend which increases the forecasts from $0.582$ to $0.599$ by the end of the forecast period, December 2020. In either case, there is an absence of a significant positive drift in the forecasts, consistent with our earlier findings. Given that the RMSE of Holt-Winters was $0.1256$, this implies that simple exponential smoothing is the most appropriate of these three techniques for forecasting monthly global temperatures.

## 统计代写|时间序列分析代写Time-Series Analysis代考|AUTOREGRESSIVE CONDITIONAL HETEROSKEDASTIC PROCESSES

10.5 Up until this point we have said nothing about how the conditional variances $\sigma_t^2$ might be generated. We now consider the case where they are a function of past values of $x_t$ :
$$\sigma_t^2=f\left(x_{t-1}, x_{t-2}, \ldots\right)$$
A simple example is:
$$\sigma_t^2=f\left(x_{t-1}\right)=\alpha_0+\alpha_1\left(x_{t-1}-\mu\right)^2$$
where $\alpha_0$ and $\alpha_1$ are both positive to ensure that $\sigma_t^2>0$. With $U_t \sim \operatorname{NID}(0,1)$ and independent of $\sigma_t, x_t=\mu+\sigma_t U_t$ is then conditionally normal,
$$x_t \mid x_{t-1}, x_{t-2}, \ldots \sim \mathrm{N}\left(\mu, \sigma_t^2\right)$$
so that
$$V\left(x_t \mid x_{t-1}\right)=\alpha_0+\alpha_1\left(x_{t-1}-\mu\right)^2$$
If $0<\alpha_1<1$ then the unconditional variance is $V\left(x_t\right)=\alpha_0 /\left(1-\alpha_1\right)$ and $x_t$ is weakly stationary. It may be shown that the fourth moment of $x_t$ is finite if $3 \alpha_1^2<1$ and, if so, the kurtosis of $x_t$ is given by $3\left(1-\alpha_1^2\right) /\left(1-3 \alpha_1^2\right)$. Since this must exceed 3, the unconditional distribution of $x_t$ is fatter tailed than the normal. If this moment condition is not satisfied, then the variance of $x_t$ will be infinite and $x_t$ will not be weakly stationary.
10.6 This model is known as the first-order autoregressive conditional het eroskedastic [ARCH(1)] process and was originally introduced by Engle (1982, 1983). ARCH processes have proven to be extremely popular for modeling volatility in time series. A more convenient notation is to define $\varepsilon_t=x_t-\mu=U_t \sigma_t$, so that the $\mathrm{ARCH}(1)$ model can be written as:
$$\begin{gathered} \varepsilon_t \mid x_{t-1}, x_{t-2}, \ldots \sim \operatorname{NID}\left(0, \sigma_t^2\right) \ \sigma_t^2=\alpha_0+\alpha_1 \varepsilon_{t-1}^2 \end{gathered}$$

# 时间序列分析代考

## 统计代写|时间序列分析代写Time-Series Analysis代考|自回归条件异方差过程

$$\sigma_t^2=f\left(x_{t-1}, x_{t-2}, \ldots\right)$$一个简单的例子是:
$$\sigma_t^2=f\left(x_{t-1}\right)=\alpha_0+\alpha_1\left(x_{t-1}-\mu\right)^2$$
where $\alpha_0$ 和 $\alpha_1$ 两者都是积极的吗 $\sigma_t^2>0$。用 $U_t \sim \operatorname{NID}(0,1)$ 独立于 $\sigma_t, x_t=\mu+\sigma_t U_t$ 那么是否有条件正常，
$$x_t \mid x_{t-1}, x_{t-2}, \ldots \sim \mathrm{N}\left(\mu, \sigma_t^2\right)$$

$$V\left(x_t \mid x_{t-1}\right)=\alpha_0+\alpha_1\left(x_{t-1}-\mu\right)^2$$

$$\begin{gathered} \varepsilon_t \mid x_{t-1}, x_{t-2}, \ldots \sim \operatorname{NID}\left(0, \sigma_t^2\right) \ \sigma_t^2=\alpha_0+\alpha_1 \varepsilon_{t-1}^2 \end{gathered}$$

## 有限元方法代写

assignmentutor™作为专业的留学生服务机构，多年来已为美国、英国、加拿大、澳洲等留学热门地的学生提供专业的学术服务，包括但不限于Essay代写，Assignment代写，Dissertation代写，Report代写，小组作业代写，Proposal代写，Paper代写，Presentation代写，计算机作业代写，论文修改和润色，网课代做，exam代考等等。写作范围涵盖高中，本科，研究生等海外留学全阶段，辐射金融，经济学，会计学，审计学，管理学等全球99%专业科目。写作团队既有专业英语母语作者，也有海外名校硕博留学生，每位写作老师都拥有过硬的语言能力，专业的学科背景和学术写作经验。我们承诺100%原创，100%专业，100%准时，100%满意。

## MATLAB代写

MATLAB 是一种用于技术计算的高性能语言。它将计算、可视化和编程集成在一个易于使用的环境中，其中问题和解决方案以熟悉的数学符号表示。典型用途包括：数学和计算算法开发建模、仿真和原型制作数据分析、探索和可视化科学和工程图形应用程序开发，包括图形用户界面构建MATLAB 是一个交互式系统，其基本数据元素是一个不需要维度的数组。这使您可以解决许多技术计算问题，尤其是那些具有矩阵和向量公式的问题，而只需用 C 或 Fortran 等标量非交互式语言编写程序所需的时间的一小部分。MATLAB 名称代表矩阵实验室。MATLAB 最初的编写目的是提供对由 LINPACK 和 EISPACK 项目开发的矩阵软件的轻松访问，这两个项目共同代表了矩阵计算软件的最新技术。MATLAB 经过多年的发展，得到了许多用户的投入。在大学环境中，它是数学、工程和科学入门和高级课程的标准教学工具。在工业领域，MATLAB 是高效研究、开发和分析的首选工具。MATLAB 具有一系列称为工具箱的特定于应用程序的解决方案。对于大多数 MATLAB 用户来说非常重要，工具箱允许您学习应用专业技术。工具箱是 MATLAB 函数（M 文件）的综合集合，可扩展 MATLAB 环境以解决特定类别的问题。可用工具箱的领域包括信号处理、控制系统、神经网络、模糊逻辑、小波、仿真等。

assignmentutor™您的专属作业导师
assignmentutor™您的专属作业导师