文章吧-经典好文章在线阅读:统计与真理读后感精选10篇

当前的位置:文章吧 > 经典文章 > 读后感 >

统计与真理读后感精选10篇

2018-01-19 21:20:02 来源:文章吧 阅读:载入中…

统计与真理读后感精选10篇

  《统计与真理》是一本由C.R.劳著作,科学出版社出版的平装图书,本书定价:22.00元,页数:132,文章吧小编精心整理的一些读者的读后感,希望对大家能有帮助

  《统计与真理》读后感(一):精华几例

  第四章讲的是有偏数据的加权分布,是理论味道最重的一章,但确实很有意思,希望我能用简单的话简要介绍一下。

  假设我们想收集这样的数据:找一个男学生,问问他家里有几个男孩,有几个女孩记录下来。这个数据显然是有偏的,因为这些家庭都至少有一个男孩。

  记家庭孩子总数N,男孩总数B(Brother),女孩总数S(Sister)。显然B+S=N,而且B>0。

  让我们考虑固定N。比方说就固定N=6吧。

  如果数据无偏,也就是我们随意调查有6个孩子的家庭,看看男孩子数B的分布是什么样的呢?

  自然,这个分布是(1,6,15,20,15,6,1)/64 二项分布嘛。

  可是数据有偏,也就是没有B=0的可能性了,怎么办的?

  办法一:把B=0的这一项删掉,分布变成了(6,15,20,15,6,1)/63,这种分布称为“截断分布”。

  办法二:把这一个男孩子扔掉不管,考虑别的孩子完全与这一个男孩无关,那么分布就应该是(1,5,10,10,5,1)/32,这种分布称为“加权分布”——也就是这一章的标题

  调查发现,实际数据更符合加权分布,而不是截断分布。

  这是个简短的比较浅显的概括,书中针对加权分布还有更详细一些的介绍,还举了别的例子。这部分理论就是作者Rao自己工作

  ------------------------------------------------------------------------

  个人认为,精华集中在三四五这三章。另外的内容就有些太通俗了。可能跟作者当时做讲座的历史情况有关,也许那时统计的思想方法还没有深入群众当中。

  第三章说了一些历史上科学界数据造假的故事,譬如著名的孟德尔豌豆遗传实验了解的人自然已经了解了,还不知道的人看了可能会比较有乐趣

  ------------------------------------------------------------------------

  第五章提出了很多很有意思的统计学应用,包括联邦党人文集作者的判定,地层年代划分,语言的谱系等等,说几个见得比较少的吧。

  1. 1947年印度刚刚独立,德里附近发生暴乱,某少数民族团体避难至受保护区域。承包商负责向政府索要生活必需用品,提供给难民。由于敌对关系难以实地调查,如何估计难民人口数量

  2. 二战期间招募士兵,由于某种罕见疾病需要进行血检。患病率很低,需要尽量减少检验工作量,怎么办?

  第五章最后还提了一个很令人惊讶结果子女SAT成绩与孩子数量负相关,同时出生的顺序也与孩子成绩负相关(越靠后分数越低)。

  ------------------------------------------------------------------------

  在最后,稍微数落一下译者吧。

  汉译本出版于2004年,我对译者在人文方面知识掌握感到非常的钦佩。

  比如,94页出现的著名人物”朱莉阿斯·西撒“,96页柏拉图”爱的盛宴“(Pheadrus),88页写了”联邦主义论文集“的”马德森“,等等。

  《统计与真理》读后感(二):第一章的不确定性其实也很赞

  其余几章的妙处我看到有人已经总结了,写的很棒,不过当我读完第一章时我就已经被这本书折服了,劳教授世界不确定性的阐述让我拍案叫绝,原来可以这么用,让我真正见识到了不确定性的美。

  下面是我读完第一章立马做的摘述。

  1、随机数列的应用

  1.1 蒙特卡洛办法

  计算矩形中不规则物体的面积,以多少点落入不规则物体,总共多少点落入矩形计算,damn right

  1.2 抽样调查,实验设计,密码,建模(利用随机断片构造一个国家不规则的海岸线)

  1.3 解决复杂问题,为推销员找最短路线,国际象棋 AI,我的理解是,由于随机数没有特性形式,但包含所有形式,那么就直接计算所有随机出来的选择,哪种最好就哪种。damn right

  1.4 对随机数列的误解

  1.4.1 如果过去几天连续出生的女孩变多,那么会增加一对夫妇生男孩的机会,哈哈!!!

  1.4.2 同一事件在短时间容易连续发生。(其实一个稳定均匀的系统可以按一定频率展示某些局部的不均匀性)

  1.4.3 大多数动物种类存货总数以3年为一周期,好像找到了自然规律(其实,任给三个随机数的集合,中间一个数最大的概率为三分之一,那么平均间隔3年就很正常了!)

  1.5 对敏感问题的随机反应经典!!!)

  让被提问者抛掷硬币,正面回答是否吸过大麻,反面回答手机尾号是否是偶数,提问者不知道对方回答的是哪一个问题,对方可以如实回答,不用担心

  a = 吸大麻的概率

  = 手机尾号为偶数的概率

  c = 回答“是”的概率

  必有 (a + b) / 0.5 = c

  damn right

  附:萧伯纳:人们需要想象那些不存在事物,而且要问它们为什么不存在。

  《统计与真理》读后感(三):摘记

  测量,重复测量,再重复测量 就能找出误差,以及误差的误差。 我的一个数学朋友告诉我说,电视台有10个气象学家,要询问每一个人明日是否有雨,如果其中有3个回答有雨,那么电视台则报道明日有雨的可能性为30%。 数学是我们并不知晓我们谈论的对象,也不关心所言及内容真假的一门科学。 ——罗素(B.Russell) It is truth very certain that when it is not in our power to determine what is true we ought to follow what is most probable. A federal appeals court has wisely corrected a gross miscalculation of government liability in a case involving weather forecasting. Last August, a U.S. District judge awarded $1.25 million to the families of three lobster-men who were drowned during a storm that had not been predicted. The judge said the government was liable because il had failed to repair promptly a wind sensor on a buoy used to help forecast weather conditions off Cape Cod. The award was overturned the other day by the appeals court or grounds that weather forecasting is a "discretionaryfunction of governmen1 and not a reliable one at that". "Weather predictions fail on frequent occasions" the appeals courl said. "If in only a small proportion of cases, parties suffering ir consequence succeeded in producing an expert who could persuade a judge that the government should have done better," the burden on the government "would be both unlimited and intolerable. " * How are the data ascertained and recorded? * Are the data free from measurement and recording errors? Are the concepts and definitions associated with measurements well defined? Are there differences between observers? *Are the data genuine, i.e., ascertained as stated, or faked or edited or adjusted in any way? Are any observations discarded at the discretion of the observer? Are there any outliers in the data which might have undue influence in statistical inference? * What is the effective population for which the observed data provides information? Is there any non-response (partial or complete) from selected units of a population under survey? Are the data obtained from a homogeneous or a mixture of populations? Are all relevant factors for identification and classification of sampled units recorded? * Is there any prior information on the problem under investigation or on the nature of observed data? Scientific laws are not advanced by the principal of authority or justified by faith or medieval philosophy; statistics is the only court of appeal to new knowledge. P.C. Mahalanobis A beautiful theory, killed by a nasty, ugly little fact. Thomas H. Huxley Supporting evidence for a scientific hypothesis is merely an attempt at falsification which failed. Every number is guilty unless proved innocent. Life is the art of drawing suflcient conclusions from insuflcient evidence. Samuel Butler To understand God's thoughts we must study statistics, for these are the measures his purpose. Francis Nightingale Science is for everybody. Not long ago, there were misconceptions and skepticisms about statistics expressed in statements such as the following: * Lies, damned lies and statistics. * Statistics is no substitute for judgement. * I know the answer, give me statistics to substantiate it. * You can prove anything by statistics. Statistics was also the subject of jokes such as * Statistics is like a bikini bathing suit. It reveals the obvious but conceals the vital. Now statistics has become a magic word to give a semblance of reality to statements we make: * Statistics prove that cigarette smoking is bad. * According to statistics, males who remain unmarried die ten * Statistically speaking tall parents have tall children. * A statistical survey has revealed that a tablet of aspirin every alternate day reduces the risk of a second heart attack. * There is statistical evidence that the second born child is less intelligent than the first, and the third born child is less intelligent than the second, and so on. * Statistics confirm that an intake of 500 mg of vitamin C every day prolongs life by six years. * A statistical survey has revealed that henpecked husbands have a greater chance of getting a heart attack. * A statistical experiment showed that students do better on a test of reasoning after hearing 10 minutes of Mozart piano sonata than they do after 10 minutes of relaxation tape or of silence. Round numbers are always false. When asked why he does not believe in astrology, the logician Raymond Smullyan responds that he is a Gemini, and Gemini never believe in astrology. Laws are not generally understood by three sorts of persons,viz. by those that make them, by those that execute them, and by those that sufler if they break them. Halifax

  《统计与真理》读后感(四):随机的大自然

  不夸张地说,这是一本巅峰我个人世界观的书。(仅仅对我而言)。我从这本书里学到最重要的一点就是随机性是自然界固有的。某些科学成就(也许是所有?)并不是依赖于因果律,而是具有统计学特征。虽然以前了解过量子不确定性还有哥德尔的不完备性,也思考过我们的物理定律本质上是不是随机的这一类问题,但当这些结论在书中被确定地说出来时还是很使我震惊。这也让我想到,其实没有什么是确定不变的(或者说绝对正确的),我们所能做的就是力图在具体的情景下做出最优决策(这否定了我以前的追求,即追求绝对正确的东西),因为大自然是随机的。

  我们生活在一个充满不确定性的世界。这种不确定性有时候让人着迷。比如人类作为拥有最高智能的生物竟然不能模仿自然界的无序!(【50】数据的伪造)比如数学家卡克竟能用确定模型的图形来模仿一个随机结构的轨迹(【20】)。另一方面,它也警示我们要随时保持开放性,也许你今天深信不疑的东西在明天就是谬误。在我看来随机性就是一个谜,它不断在有序和无序之间飘来荡去。然而它的本质是什么?

  统计学可以帮助我们利用不确定性。它不讲形而上学而讲究实效。在数据泛滥的今天,统计学在生活中的应用随处可见。以致我们常有这么一种观点,不要吹得天花乱坠,摆出你的数据来。我们常以为数据就是事实。作者却告诉我们,不一定。数据有干净不干净之分。样本的选择是否合理?采集数据过程是否有误差?数据是否是伪造的?选择怎样的随机结构来使用数据?这些都可能导出一个错误的结论。因此对那些由“确凿数据”得出的结论,我们需要保持警惕。而统计学可以帮助我们辨别真伪。

  作者在第五章将统计学的应用在我看来是全书最精彩的部分。统计学真是一门奇妙的学科,以致我觉得没学过统计学的人是不完整的…(准备啃书去)

评价:

[匿名评论]登录注册

评论加载中……