• 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

Random (or approximately random) sampling-as well as the more advanced kinds of sampling discussed in optional Section 1.7–are types of probability sampling. In general, probability sampling is sampling where we know the chance (or probability) that each element in the population will be included in the sample. If we employ probability sampling, the sample obtained can be used to make valid statistical inferences about the sampled population. However, if we do not employ probability sampling, we cannot make valid statistical inferences.

One type of sampling that is not probability sampling is convenience sampling, where we select elements because they are easy or convenient to sample. For example, if we select people to interview because they look “nice” or “pleasant,” we are using convenience sampling. Another example of convenience sampling is the use of voluntary response samples, which are frequently employed by television and radio stations and newspaper columnists. In such samples, participants self-select-that is, whoever wishes to participate does so (usually expressing some opinion). These samples overrepresent people with strong (usually negative) opinions. For example, the advice columnist Ann Landers once asked her readers, “If you had it to do over again, would you have children?” Of the nearly 10,000 parents who voluntarily responded, 70 percent said that they would not. A probability sample taken a few months later found that 91 percent of parents would have children again.

Another type of sampling that is not probability sampling is judgment sampling, where a person who is extremely knowledgeable about the population under consideration selects population elements that he or she feels are most representative of the population. Because the quality of the sample depends upon the judgment of the person selecting the sample, it is dangerous to use the sample to make statistical inferences about the population.

To conclude this section, we consider a classic example where two types of sampling errors doomed a sample’s ability to make valid statistical inferences. This example occurred prior to the presidential election of 1936 , when the Literary Digest predicted that Alf Landon would defeat Franklin D. Roosevelt by a margin of 57 percent to 43 percent. Instead, Roosevelt won the election in a landslide. Literary Digest’s first error was to send out sample ballots (actually, 10 million ballots) to people who were mainly selected from the Digest’s subscription list and from telephone directories. In 1936 the country had not yet recovered from the Great Depression, and many unemployed and low-income people did not have phones or subscribe to the Digest. The Digest’s sampling procedure excluded these people, who overwhelmingly voted for Roosevelt. Second, only $2.3$ million ballots were returned, resulting in the sample being a voluntary response survey. At the same time, George Gallup, founder of the Gallup Poll, was beginning to establish his survey business. He used a probability sample to correctly predict Roosevelt’s victory. In optional Section $1.8$ we discuss various issues related to designing surveys and more about the errors that can occur in survey samples.

统计代写|商业分析作业代写Statistical Modelling for Business代考|Ethical guidelines for statistical practice

The American Statistical Association, the leading U.S. professional statistical association, has developed the report “Ethical Guidelines for Statistical Practice.” 11 This report provides information that helps statistical practitioners to consistently use ethical statistical practices

and that helps users of statistical information avoid being misled by unethical statistical practices. Unethical statistical practices can take a variety of forms, including:

• Improper sampling Purposely selecting a biased sample_for example, using a nonrandom sampling procedure that overrepresents population elements supporting a desired conclusion or that underrepresents population elements not supporting the desired conclusion-is unethical. In addition, discarding already sampled population elements that do not support the desired conclusion is unethical. More will be said about proper and improper sampling later in this chapter.
• Misleading charts, graphs, and descriptive measures In Section 2.7, we will present an example of how misleading charts and graphs can distort the perception of changes in salaries over time. Using misleading charts or graphs to make the salary changes seem much larger or much smaller than they really are is unethical. In Section 3.1, we will present an example illustrating that many populations of individual or household incomes contain a small percentage of very high incomes. These very high incomes make the population mean income substantially larger than the population median income. In this situation we will see that the population median income is a better measure of the typical income in the population. Using the population mean income to give an inflated perception of the typical income in the population is unethical.
• Inappropriate statistical analysis or inappropriate interpretation of statistical results The American Statistical Association report emphasizes that selecting many different samples and running many different tests can eventually (by random chance alone) produce a result that makes a desired conclusion seem to be true, when the conclusion really isn’t true. Therefore, continuing to sample and run tests until a desired conclusion is obtained and not reporting previously obtained results that do not support the desired conclusion is unethical. Furthermore, we should always report our sampling procedure and sample size and give an estimate of the reliability of our statistical results. Estimating this reliability will be discussed in Chapter 7 and beyond.

The above examples are just an introduction to the important topic of unethical statistical practices. The American Statistical Association report contains 67 guidelines organized into eight areas involving general professionalism and ethical responsibilities. These include responsibilities to clients, to research team colleagues, to research subjects, and to other statisticians, as well as responsibilities in publications and testimony and responsibilities of those who employ statistical practitioners.

Descriptive analytics
In previous examples we have introduced dot plots, time series plots, bar charts, and histograms and illustrated their use in graphically displaying data. These and other traditional graphicalmethods for displaying data are fully discussed in Chapter 2 . These methods, and more recently developed statistical display techniques designed to take advantage of the dramatic advances in data capture, transmission and storage, make up the toolset of descriptive analytics. Descriptive analytics uses the traditional and or newer graphics to present to executives (and sometimes customers) easy-to-understand visual summaries of up-to-the minute information concerning the operational status of a business. In optional Section $2.8$, we will discuss some of the new graphics, which include gauges, bullet graphs, treemaps, and sparklines. We will also see how they are used with each other and more traditional graphics to form analytic dushbourds, which are part of execuive injormaion sysiems. As an example of une of the new graphics-the bullet graph -we again consider the Disney Parks Case.

统计代写|商业分析作业代写Statistical Modelling for Business代考|Ethical guidelines for statistical practice

• 抽样不当 故意选择有偏差的样本（例如，使用非随机抽样程序，该程序过度代表支持预期结论的总体元素或未充分代表不支持预期结论的总体元素）是不道德的。此外，丢弃不支持预期结论的已抽样人口元素是不道德的。本章稍后将详细介绍正确和不正确的抽样。
• 误导性图表、图表和描述性度量 在第 2.7 节中，我们将展示一个示例，说明误导性图表和图表如何扭曲对工资随时间变化的看法。使用误导性图表或图表使工资变化看起来比实际大得多或小得多是不道德的。在第 3.1 节中，我们将展示一个示例，说明许多个人或家庭收入人群中只有一小部分收入非常高。这些非常高的收入使人口平均收入大大高于人口平均收入。在这种情况下，我们将看到人口中位数收入是衡量人口典型收入的更好指标。使用人口平均收入来夸大人口中的典型收入是不道德的。
• 不恰当的统计分析或对统计结果的不恰当解释 美国统计协会的报告强调，选择许多不同的样本并运行许多不同的测试最终会（仅凭随机机会）产生一个结果，使期望的结论看起来是真实的，而结论确实不是真的。因此，继续采样和运行测试直到获得所需的结论，并且不报告先前获得的不支持所需结论的结果是不道德的。此外，我们应该始终报告我们的抽样程序和样本量，并估计我们的统计结果的可靠性。估计这种可靠性将在第 7 章及以后讨论。

广义线性模型代考

statistics-lab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。