### 物理代写|统计力学代写Statistical mechanics代考|PHYSICS 7546

statistics-lab™ 为您的留学生涯保驾护航 在代写统计力学Statistical mechanics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。我们的专家在代写统计力学Statistical mechanics代写方面经验极为丰富，各种代写统计力学Statistical mechanics相关的作业也就用不着说。

• Statistical Inference 统计推断
• Statistical Computing 统计计算
• Advanced Probability Theory 高等概率论
• Advanced Mathematical Statistics 高等数理统计学
• (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

## 物理代写|统计力学代写Statistical mechanics代考|“Subjective” Versus “Objective” Probabilities

As we said, there are, broadly speaking, two different meanings given to the word ‘probability’ in the natural sciences. The first notion is the so-called “objective” or “frequentist” one, namely the view of probability as something like a “theoretical frequency”: if one says that the probability of the event $E$ under condition $X, Y, Z$ equals $\mathrm{p}$, one means that, if one reproduces the ‘same’ conditions $X, Y, Z$ “sufficiently often”, the event E will appear with frequency p. Of course, since the world is constantly changing, it is not clear what reproducing the ‘same’ conditions means exactly; besides, the expression “sufficiently often” is vague and this is the source of much criticism of that notion of probability. ${ }^{2}$ But, putting those objections aside for a moment, probabilistic statements are, according to the “frequentist” view, factual statements that can in principle be confirmed or refuted by observations or experiments. We will come back to the discussion of the frequentist view in Sect. $2.4$ below, but now we will turn to the other meaning of the word ‘probability’, the “subjective” or Bayesian one.

In this approach, probabilities refer to a form of reasoning and not to a factual statement. Assigning a probability to an event expresses a judgment on the likelihood of that single event, based on the information available at that moment. Note that, here, one is not interested in what happens when one reproduces many times the ‘same’ event, as in the objective approach, but in the probability of a single event. This is of course very important in practice: when I wonder whether I need to take my umbrella because it may rain, or whether the stock market will crash next week, I am not mainly interested in the frequencies with which such events occur but with what will happen here and now; of course, these frequencies may be part of the information that is used in arriving at a judgment on the probability of a single event, but, typically, they are not the only information available.

One may even ask probabilistic questions, like “what is the probability of life or of intelligent life in the universe or in our galaxy?” or “what is the probability that the value of a given physical constants lies in a given interval” that do not make sense from a frequentist point of view. ${ }^{3}$ Yet, people do try to answer these questions; those answers may not be better than educated guesses, but these examples show that our intuitive notion of probability is not restricted to theoretical frequencies.

Note that, to add to the confusion, one has to make a distinction between the “objective” or “rational” Bayesian approach and the “subjective” Bayesian approach. In the latter approach, which was championed among others by the Italian mathematician de Finetti $[93,94]$, probabilities can be assigned more or less arbitrarily, provided one follows the rules of probability, like
$$P(A \cup B)=P(A)+P(B)$$
whenever $A \cap B=\emptyset$

## 物理代写|统计力学代写Statistical mechanics代考|The Indifference Principle

This principle says: first, list a series of possibilities for a “random” event, about which we know nothing, namely that we have no reason to think that one of them is more likely to occur than another one (so that “we are equally ignorant” with respect to all those possibilities). Then, assign to each of them an equal probability. If there are $N$ possibilities, we have:
$$\begin{gathered} P(i)=\frac{1}{N} \ \forall i=1, \ldots, N \end{gathered}$$

This “principle” is just another expression of our equal ignorance. ${ }^{7}$
There are many problems with this definition and several objections have been raised against it. First of all, when are we in this situation of indifference? In games of chance where there is a symmetry between the different outcomes of the random event (tossing of a coin, throwing of a die, roulette wheels etc.) it is easy to apply the indifference principle. But for more complicated situations, it is not obvious how to proceed.

Some people object that we use our ignorance to gain some information about that random event: at first, we do not know anything about it and from that we deduce that all those events are equally probable. But, from a subjectivist view of probabilities, not knowing anything about a series of possibilities and saying that all those possibilities have equal probabilities are equivalent statements, since, in that view, a probability statement is not a statement about the world but about our state of knowledge.

In more complicated situations, where there is no symmetry between the different possibilities one uses the maximum entropy principle. Namely one assigns to each probability distribution $\mathbf{p}=\left(p_{i}\right){i=1}^{N}$ over $N$ objects its Shannon entropy, given by: $$S(\mathbf{p})=-\sum{i=1}^{N} p_{i} \log p_{i}$$
One then chooses the probability distribution that has the maximum entropy, among those that satisfy certain constraints that incorporate the information that we have about the system.

The rationale behind this principle, as for the indifference principle, is not to introduce bias in our judgments, namely information that we do not have (like people who believe in lucky numbers). And one can argue that maximizing the Shannon entropy is indeed the best way to formalize that notion. We will discuss in detail this idea and its justification in Sect. 7.2, see also Shannon [291] and Jaynes [180], [183, Sect. 11.3].

## 物理代写|统计力学代写Statistical mechanics代考|Cox’ “Axioms” and Theorem

As an aside, let us mention also that, in 1946, Cox [90], inspired by previous ideas of Keynes [190], gave a foundation to the “subjective” approach to probability based on reasonings about the plausibility of propositions (see Jaynes [183] for an extensive discussion of this approach). Instead of assigning probabilities to events, as in elementary probabilities, or to sets, as in the mathematical version (see Appendix 2.A), Cox gives a numerical value to the plausibility $\mathcal{P}(p \mid q)$ of a proposition $p$ given that another proposition $q$ is true. ${ }^{8}$

Then, Cox imposes some rules of rationality on those plausibility assignments and derive from them, for a given proposition $\mathrm{r}$, the sum rule:
$$\mathcal{P}(p \text { or } q \mid r)=\mathcal{P}(p \mid r)+\mathcal{P}(q \mid r)-\mathcal{P}(p \text { and } q \mid r),$$
and the product rule:
$\mathcal{P}(p$ and $q \mid r)=\mathcal{P}(p \mid q$ and $r) \mathcal{P}(q \mid r)=\mathcal{P}(q \mid p$ and $r) \mathcal{P}(p \mid r)$
If we replace the propositions by sets (e.g. sets of events that render the propositions true), (2.2.3), expressed in terms of probabilities of sets, means:
$$P(A \cup B)=P(A)+P(B)-P(A \cap B),$$
which reduces to (2.2.1) when $p$ and $q$ are incompatible, namely when the sets $A$ and $B$ of events for which those propositions are true are disjoint; besides (2.2.5) follows by applying (2.2.1) to the disjoint union $A \cup B=(A \backslash B) \cup(B \backslash A) \cup(A \cap B)$ and using $A=(A \backslash B) \cup(A \cap B)$ and $B=(B \backslash A) \cup(A \cap B)$.
Equation (2.2.4), expressed in terms of probabilities of sets, means:
$$P(A \cap B \mid C)=P(A \mid B \cap C) P(B \mid C)=P(B \mid A \cap C) P(A \mid C),$$
where by definition,
$$P(A \mid B)=\frac{P(A \cap B)}{P(B)}$$
is the conditional probability of event $A$ given event $B$.

## 有限元方法代写

tatistics-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。