统计学的世界（第五版）
On Being a Scientist 3rd Edition
医学统计学第二版 12.4MB 孙振球主编教材光盘 < 一张光盘>
The Cochrane Library 2007, Issue 2 1.99GB < 四张光盘外加虚拟光驱achol>
http://d.namipan.com/d/c427b5ca52716a5635bba5fe8445b415b746c3856824c700
http://d.namipan.com/d/80cd22d25bd5e965b6f44d35cac71392e417693904130600
http://d.namipan.com/d/fe70f34c236128586265eab1aa4e7a51ee6ae5cb6f864600
http://d.namipan.com/d/98f3b5046a241e0a63ec12fbfa0e45ab5a43ac3bf801f57f
http://www3.interscience.wiley.com/cgi-bin/mrwhome/106568753/EvidenceAid.html
http://www.cochrane.org/evidenceaid/haiti/
http://cochrane.bireme.br/portal/php/index.php
A full collection of resources is available at www.cochrane.org/evidenceaid/haiti/. Please find below the free full text (pdf format) for a selection of relevant systematic reviews from The Cochrane Library. Please note that many countries have full text access to the html versions of these reviews via the Virtual Health Library BIREME interface (in English, Spanish or Portuguese) or via this website through their institution. In addition, all residents of countries in the World Bank’s list of low-income economies (countries with a gross national income (GNI) per capita of less that $1000) have free one-click access to all Cochrane reviews, including Haiti. During this time, Wiley have also made country-wide free access available to the Dominican Republic and Panama.
Contact: Mike Clarke (mclarke@cochrane.ac.uk), Director of the UK Cochrane Centre, for more information or to suggest other topics.
We recommend selecting the PDF version if you do not hold a licence to The Cochrane Library, so that you may view the Standard PDF free of charge.
Prevention of waterborne infections
Interventions to improve water quality for preventing diarrhoea (HTML) (PDF)
Wound management
Tissue adhesives for traumatic lacerations in children and adults (HTML) (PDF)
Water for wound cleansing (HTML) (PDF)
Honey as a topical treatment for wounds (HTML) (PDF)
Fracture management
Distal radius fracture
Anaesthesia for treating distal radial fracture in adults (HTML) (PDF)
Bone grafts and bone substitutes for treating distal radial fractures in adults (HTML) (PDF)
Conservative interventions for treating distal radial fractures in adults (HTML) (PDF)
External fixation versus conservative treatment for distal radial fractures in adults (HTML) (PDF)
Percutaneous pinning for treating distal radial fractures in adults (HTML) (PDF)
Proximal humeral fracture
Interventions for treating proximal humeral fractures in adults (HTML) (PDF)
General fracture management
Antibiotics for preventing infection in open limb fractures (HTML) (PDF)
Fractures in children
Interventions for treating wrist fractures in children (HTML) (PDF)
Physical trauma (excluding fractures)
Fluid resuscitation
Colloids versus crystalloids for fluid resuscitation in critically ill patients (HTML) (PDF)
Brain injury
Corticosteroids for acute traumatic brain injury (HTML) (PDF)
Hypothermia for traumatic head injury (HTML) (PDF)
Mannitol for acute traumatic brain injury (HTML) (PDF)
Psychological treatment for anxiety in people with traumatic brain injury (HTML) (PDF)
Spinal cord injury
Steroids for acute spinal cord injury (HTML) (PDF)
Gangliosides for acute spinal cord injury (HTML) (PDF)
Blood transfusion
Anti-fibrinolytic use for minimising perioperative allogeneic blood transfusion (HTML) (PDF)
Cell salvage for minimising perioperative allogeneic blood transfusion (HTML) (PDF)
Desmopressin use for minimising perioperative allogeneic blood transfusion (HTML) (PDF)
Fibrin sealant use for minimising peri-operative allogeneic blood transfusion (HTML) (PDF)
Recombinant factor Vlla for the prevention and treatment of bleeding in patients without haemophilia (HTML) (PDF)
Transfusion thresholds and other strategies for guiding allogeneic red blood cell transfusion (HTML) (PDF)
Post-traumatic stress disorder
Psychological treatment of post-traumatic stress disorder (PTSD) (HTML) (PDF)
Psychological debriefing for preventing post traumatic stress disorder (PTSD) (HTML) (PDF)
Renal
Emergency interventions for hyperkalaemia (HTML) (PDF)
Intermittent versus continuous renal replacement therapy for acute renal failure in adults (HTML) (PDF)
图3 MoCA量表筛查MCI灵敏度高于MMSE
天路客按：“《论语·卫灵公》有言曰：“工欲善其事，必先利其器。居是邦也，事其大夫之贤者，友其士之仁者。”作为中国人相比都耳熟能详，这话的意思是要做好工作，先要使工具锋利。小说里面也有这话，如：“工欲善其事，必先利其器。今既一无所有，纵使大禹重生，亦当束手。”（清·李汝珍《镜花缘》第三十六回）。”（见天路客《现代方法学的进步终会打破中医残梦——兼谈中医缺少证伪能力》XYS20091104），科学有效的方法固然重要，但也不要迷信，惟方法论，任何方法学（Methodology）都是有局限的，都不是绝对的，不能唯方法论，否则科学方法更会使人迷失，一个清醒的人要避免被方法所掌握，即使RCT也远非万能，特转载此文以作说明，有兴趣者可以继续讨论。
文章来源：BMJ 2003;327:1459-1461 (20 December), doi:10.1136/bmj.327.7429.1459
Gordon C S Smith, professor1, Jill P Pell, consultant2
1 Department of Obstetrics and Gynaecology, Cambridge University, Cambridge CB2 2QQ, 2 Department of Public Health, Greater Glasgow NHS Board, Glasgow G3 8YU
Correspondence to: G C S Smith gcss2@cam.ac.uk
Objectives To determine whether parachutes are effective in preventing major trauma related to gravitational challenge.
Design Systematic review of randomised controlled trials.
Data sources: Medline, Web of Science, Embase, and the Cochrane Library databases; appropriate internet sites and citation lists.
Study selection: Studies showing the effects of using a parachute during free fall.
Main outcome measure Death or major trauma, defined as an injury severity score > 15.
Results We were unable to identify any randomised controlled trials of parachute intervention.
Conclusions As with many interventions intended to prevent ill health, the effectiveness of parachutes has not been subjected to rigorous evaluation by using randomised controlled trials. Advocates of evidence based medicine have criticised the adoption of interventions evaluated by using only observational data. We think that everyone might benefit if the most radical protagonists of evidence based medicine organised and participated in a double blind, randomised, placebo controlled, crossover trial of the parachute.
The parachute is used in recreational, voluntary sector, and military settings to reduce the risk of orthopaedic, head, and soft tissue injury after gravitational challenge, typically in the context of jumping from an aircraft. The perception that parachutes are a successful intervention is based largely on anecdotal evidence. Observational data have shown that their use is associated with morbidity and mortality, due to both failure of the intervention1 2 and iatrogenic complications.3 In addition, “natural history” studies of free fall indicate that failure to take or deploy a parachute does not inevitably result in an adverse outcome.4 We therefore undertook a systematic review of randomised controlled trials of parachutes.
Literature search
We conducted the review in accordance with the QUOROM (quality of reporting of meta-analyses) guidelines.5 We searched for randomised controlled trials of parachute use on Medline, Web of Science, Embase, the Cochrane Library, appropriate internet sites, and citation lists. Search words employed were “parachute” and “trial.” We imposed no language restriction and included any studies that entailed jumping from a height greater than 100 metres. The accepted intervention was a fabric device, secured by strings to a harness worn by the participant and released (either automatically or manually) during free fall with the purpose of limiting the rate of descent. We excluded studies that had no control group.
Definition of outcomes
The major outcomes studied were death or major trauma, defined as an injury severity score greater than 15.6
Meta-analysis
Our statistical apprach was to assess outcomes in parachute and control groups by odds ratios and quantified the precision of estimates by 95% confidence intervals. We chose the Mantel-Haenszel test to assess heterogeneity, and sensitivity and subgroup analyses and fixed effects weighted regression techniques to explore causes of heterogeneity. We selected a funnel plot to assess publication bias visually and Egger’s and Begg’s tests to test it quantitatively. Stata software, version 7.0, was the tool for all statistical analyses.
Our search strategy did not find any randomised controlled trials of the parachute.
 |
| Parachutes reduce the risk of injury after gravitational challenge, but their effectiveness has not been proved with randomised controlled trials
Credit: HULTON/GETTY
|
Discussion
Evidence based pride and observational prejudice
It is a truth universally acknowledged that a medical intervention justified by observational data must be in want of verification through a randomised controlled trial. Observational studies have been tainted by accusations of data dredging, confounding, and bias.7 For example, observational studies showed lower rates of ischaemic heart disease among women using hormone replacement therapy, and these data were interpreted as advocating hormone replacement for healthy women, women with established ischaemic heart disease, and women with risk factors for ischaemic heart disease.8 However, randomised controlled trials showed that hormone replacement therapy actually increased the risk of ischaemic heart disease,9 indicating that the apparent protective effects seen in observational studies were due to bias. Cases such as this one show that medical interventions based solely on observational data should be carefully scrutinised, and the parachute is no exception.
Natural history of gravitational challenge
The effectiveness of an intervention has to be judged relative to non-intervention. Understanding the natural history of free fall is therefore imperative. If failure to use a parachute were associated with 100% mortality then any survival associated with its use might be considered evidence of effectiveness. However, an adverse outcome after free fall is by no means inevitable. Survival has been reported after gravitation challenges of more than 10 000 metres (33 000 feet).4 In addition, the use of parachutes is itself associated with morbidity and mortality.1-3 10 This is in part due to failure of the intervention. However, as with all interventions, parachutes are also associated with iatrogenic complications.3 Therefore, studies are required to calculate the balance of risks and benefits of parachute use.
The parachute and the healthy cohort effect
One of the major weaknesses of observational data is the possibility of bias, including selection bias and reporting bias, which can be obviated largely by using randomised controlled trials. The relevance to parachute use is that individuals jumping from aircraft without the help of a parachute are likely to have a high prevalence of pre-existing psychiatric morbidity. Individuals who use parachutes are likely to have less psychiatric morbidity and may also differ in key demographic factors, such as income and cigarette use. It follows, therefore, that the apparent protective effect of parachutes may be merely an example of the “healthy cohort” effect. Observational studies typically use multivariate analytical approaches, using maximum likelihood based modelling methods to try to adjust estimates of relative risk for these biases. Distasteful as these statistical adjustments are for the cognoscenti of evidence based medicine, no such analyses exist for assessing the presumed effects of the parachute.
The medicalisation of free fall
It is often said that doctors are interfering monsters obsessed with disease and power, who will not be satisfied until they control every aspect of our lives (Journal of Social Science, pick a volume). It might be argued that the pressure exerted on individuals to use parachutes is yet another example of a natural, life enhancing experience being turned into a situation of fear and dependency. The widespread use of the parachute may just be another example of doctors’ obsession with disease prevention and their misplaced belief in unproved technology to provide effective protection against occasional adverse events.
|
Parachutes and the military industrial complex
However sinister doctors may be, there are powers at large that are even more evil. The parachute industry has earned billions of dollars for vast multinational corporations whose profits depend on belief in the efficacy of their product. One would hardly expect these vast commercial concerns to have the bravery to test their product in the setting of a randomised controlled trial. Moreover, industry sponsored trials are more likely to conclude in favour of their commercial product,11 and it is unclear whether the results of such industry sponsored trials are reliable.
A call to (broken) arms
Only two options exist. The first is that we accept that, under exceptional circumstances, common sense might be applied when considering the potential risks and benefits of interventions. The second is that we continue our quest for the holy grail of exclusively evidence based interventions and preclude parachute use outside the context of a properly conducted trial. The dependency we have created in our population may make recruitment of the unenlightened masses to such a trial difficult. If so, we feel assured that those who advocate evidence based medicine and criticise use of interventions that lack an evidence base will not hesitate to demonstrate their commitment by volunteering for a double blind, randomised, placebo controlled, crossover trial.
Contributors: GCSS had the original idea. JPP tried to talk him out of it. JPP did the first literature search but GCSS lost it. GCSS drafted the manuscript but JPP deleted all the best jokes. GCSS is the guarantor, and JPP says it serves him right.
Competing interests: None declared.
Ethical approval: Not required.
对照研究中一定要注意研究组间基线资料的可比性
———评近来关于中国的基础教育好坏的讨论
作者：天路客
拜读了网友金海的文章《再看钱学森论教育的问题》，讨论了中国的“人才”问题和教育问题，也拜读了未火的评论文章《说中国的基础教育好有什么根据？》，我比较倾向于未火网友。
统计学上强调对照的原则，目的无非是为了增加两组之间的可比性，增加研究结果的真实性。两组之间的比较，不仅仅是研究结果的分析比较，更重要的是要注意在研究开始时，两组之间的基本数据是否有可比性（compatibility），也就是说这涉及到分组的方法问题，以及分组后两组的资料数据是否平衡的问题。
统计学中有个基本概念“基线”（baseline），所谓基线是指研究措施执行前，被研究对象的基本特征。具体到文章中涉及到的问题，因素有很多，未火网友也说到了一部分，不再重复，实际上，同一个研究方法或者同一种处理措施，在不同的研究中，得到不同的结果，往往是由于被研究对象之间的基线资料差别所致。
在研究中一定要对得到的数据作进一步的分析，确保基线资料的平衡，这样研究结果才有意义，才有说服力。所以，统计学中一般会对资料做可比性分析、变异因素分析等，这里就不展开了，有兴趣但又不太清楚的朋友们可以自己查资料了解一下。
保证结果可靠的关键是一定要保证基线资料的可比性，具体操作起来也不是一两句话说得清楚，简单说一下，一般会有如下措施（本文不是讨论统计学，都不展开说明）：
确定受试对象的选择条件
制定统一的检测标准
必要时分层分组
防止向均数回归现象的影响
减少基线资料的变异
所以，未火的说法还是比较靠谱的，选择适当的数学模型采用适当的统计方法才能得出比较准确的结论，金海的结论的是建立在基线资料可比性不强的基础上泛泛得出来的。
2009.11.21
天路客
看了一则旧闻（《中医专家指西医统计学为贬低中医首因》北京晨报2008年02月01日），文章的其中一段如下：
“为什么都认为中医的治疗能力不行呢？就是统计的方法造成的。”他举了个例子，当年，他父亲行医的时候，曾经治愈过197例小儿麻疹。虽然是同一种病，却用了30多种处方。但是在西医的统计学里，这些并不被认可。因为西医的评价体系是用一个处方要把197例都给药好。统计学恰恰认为能够杀灭细菌病毒才算成功，才能被记入治愈率，这样一来，中医就吃了大亏。其实，通过中医治疗，能够使患者恢复健康的病例远比西医要多。”关庆维说。“最显著的一点是，不同的人得了相同的病，西医用药相同，而中医却是一个人一种药方，上万种药材的排列组合是非常复杂的，是针对每个人的自身状况不同对症下药。这样复杂的组合排列要求中医大夫有足够的临床经验，和对每一味药材的了解，这也限制了中医成材的难度。”
看了文章题目我还以为中医专家们都成了统计学专家了呢，原来貌似什么是统计学这位“专家”都没有搞清楚，即使不按这位专家所说的“西医的统计学”标准（按：我还是第一次听说这种说法，难道还有个中医的统计学？），不知这位专家所谓他父亲治愈病人的根据是什么？很显然，这位中医”专家”说的话也是很不严谨的，原因找错了！
不从事物自身找原因，总是找一些所谓的理由，不知这位专家在文章中说的“其实，… …而中医却是一个人一种药方，上万种药材的排列组合是非常复杂的，是针对每个人的自身状况不同对症下药。这样复杂的组合排列要求中医大夫有足够的临床经验，和对每一味药材的了解，这也限制了中医成材的难度。”这样的话是否有根有据还是有目的的信口开河？
有哪一位中医是在上万种中药材的排列组合中处方的呢？我是没有见过！《神农本草经》不过载药365种、《本草纲目》载药也不过2000种，常用药就更少了。这不到2000种药物里面还包括里面那些乌七八糟的“药物”，随便举个例子，有兴趣的可以翻阅未删节本《本草纲目》的“人部”，看看里面都有些什么东西，保你大开眼界！难道这些也在这位专家处方时的排列组合之列？不信可以任意找任意数量的中医开的处方做统计，看看他们涉及到的药物到底有多少种。虽然1999年通过的全国普查，使目前中药总数达到了12800余种，但也只是统计上的意义，并非常用药物，常用药物无非就那么几百味，这其中还包括大量的重金属等指标超标的药物，莫非这位专家把这12800种药物都运用自如？
现在来分析这位专家关于统计学的说法，分析是否是“为什么都认为中医的治疗能力不行呢？就是统计的方法造成的。”？是否是“当年，他父亲行医的时候，曾经治愈过197例小儿麻疹。虽然是同一种病，却用了30多种处方。但是在西医的统计学里，这些并不被认可。”？我不相信这30多种处方用的是完全不同的药物，也只不过某方加减而已，其中大部分药物的使用还是相同的，个别药物不同而已，统计学上处理起来很简单，做个合适的回归分析就可以了，即使再加上时间因素来分析，也不难，统计学发展到现在的水平，可供使用的数学模型也不是没有，例如COX回归就可以解决这个问题。
所以，问题的症结不在是否是统计学的问题，即使没有统计学，中医还会吃别的学的亏，这是一定的了，只要中医建立不起来诊断标准，做不到标准客观，随意解释的话，永远不可能不吃亏。
中医吃了统计亏？中医运用几万种药物排列组合？也许吧！
“伪随机”数不是“假随机”数
———— 评奥卡姆剃刀评《天路客评<通过比喻理解“大样本随机双盲对照临床试验”>》
作者：天路客
首先回答关于第二个问题，文章发出后，我觉得有的地方说法欠妥，考虑到文章已发出，就没有及时通知更正作进一步的说明，现在也还没有想好怎么论述这个问题。
至于第一个问题，“随机”的概念严格说来不是统计学的基本概念，但却是更基本的东西。在医学统计学中，对“随机”概念并不作介绍，基本概念中也不介绍，为避免不太了解的朋友产生误会，我略作一下说明。
首先说明一点：计算机不会产生绝对随机的随机数，这是确定的。
那怕计算机技术（这里指据冯诺依曼思想发展起来的电子计算机）发展到什么程度，也只是能够产生一串“伪随机”（ pseudo-random）数，不会产生绝对“真”的随机数。其实，设定一个程序后，随机数的计算方法在不同的计算机中是不同的，即使在相同的计算机中安装的不同的操作系统中也是不同的、相同的随机种子在不同计算机或系统中生成的随机数也不同。
计算机的伪随机数是由随机种子根据一定的计算方法算出来的，而随机种子如果没有特殊规定在默认情况下一般来自系统时钟，所以，只要计算方法一定，随机种子一定，那么产生的随机数就是固定的。
绝对随机的随机数字只是一种理想状态，举个不太恰当的比喻，随机数字序列就像物理学中讲的“质点”，将物体简化后得到的只有质量而不计大小、形状的一个几何点，这是经典力学中常用的理想化模型，是实际物体在一定条件下的科学抽象。
所以说，所谓“伪随机数”只是一种相对的随机数，就是说，是有规律的随机数，也就是奥卡姆剃刀朋友所说的“过足够长的一段后，可能出现与前面完全相同的序列。”
但是，这里所说的“伪”不是“假”，应该理解为“有规律”比较确切，也就是说计算机（例如通过统计软件包SAS等）产生的随机数既是随机的又是有规律的，但说到底还算随机数即使是“伪随机数”，也许将来的计算机会产生基于自然规律的不可重复的“真”随机数，但这里的真还是得加上一个引号。
在生物、医学或工程的常规科研中，伪随机数已经足够用了，只要不搞成假随机。
至于在实验中到处可见的闭着眼睛抓白鼠之类的“随机”我实在看不出有多少益处。
“伪随机”数不是“假随机”数
天路客
bangbu1996在该文中说：“比就比，李婆拿出十个苹果，可她眼花；王婆也拿出十个苹果，可她眼毒着呢。这不用比，王婆的苹果好。慢着，消费者可不是被骗大的，两个婆婆都蒙住眼，随便从箱里摸出十个来比比。最后是李婆的苹果好。嘿嘿，这个就是“随机”的意义。”
从统计学来说，这个比方并不恰当，这样并不构成随机，而是直接编号，使用随机数字表、计算器或者使用用SAS编制程序来构成随机。
另，在“买苹果，王婆打开了一箱。“又甜又脆的苹果喽！不甜不脆不要钱”，说的好听！当然了，卖苹果的说的都好听。如果你是个智力正常的消费者，不需要考虑就会挑几个看看。不错，确实没有烂的。但是只看“几个”是不够的，最好把整箱都翻看一遍才放心。只是你没有时间，或者王婆也不让干。那么，你检验的越多，“这一箱苹果都是好的”的可能性就越大。这就是“大样本”的意义。”一段中，“那么，你检验的越多，“这一箱苹果都是好的”的可能性就越大。”
这样说也不确切，也有可能“这一箱苹果都是好的”的可能性越小，如果烂苹果多些的话。
与bangbu1996朋友商榷。
