参考文献

参考文献 导言:思维胜于数据 注释书目

Hacking(1990和Stigler(1986,1999,2016深入探讨了从古至今的概率统计历史。Salsburg(2002的内容技术含量较低。遗憾的是,尽管Hoover(2008)、Kleinberg(2015),Losee(2012)、Mumford和Anjum(2014都包含一些有趣的资料,但它们都缺乏对因果思维历史的全面描述。从几乎所有的标准统计学教科书中,我们都可以看到对因果描述的禁令,例如,Freedman、Pisani和Purves(2007或者Efron和Hastie(2016。关于这种禁令作为语言障碍的分析,见Pearl(2009,第5章和第11章),以及其作为文化障碍的分析,见Pearl(2000b)。

关于大数据和机器学习的成就和局限性的最新介绍见Darwiche(2017)、Pearl(2017)、Mayer-Schönberger和Cukier(2013)、Domingos(2015)、Marcus(2017)。Toulmin(1961)为这场辩论提供了历史背景。

对“模型发现”和do算子的更多技术处理感兴趣的读者可以翻阅Pearl(1994,2000a,第2~3章),Spirtes、Glymour和Scheines(2000)。有关这些概念的更细致的介绍,请参阅Pearl、Glymour和Jewell(2016)。这篇参考文献是推荐给具有大学数学的水平,但没有统计学或计算机科学背景的读者的。它还提供了关于条件概率、贝叶斯法则、回归和相应图示的基本介绍。

图0.1所示的因果推断引擎的早期版本可在Pearl(2012)、Pearl和Bareinbeim(2014)中找到。

参考文献

Darwiche, A. (2017). Human-level intelligence or animal-like abilities? Tech.rep., Department of Computer Science, University of California, Los Angeles,CA. Submitted to Communications of the ACM. Accessed online at https://arXiv:1707.04327.

Domingos, P. (2015). The Master Algorithm: How the Quest for the Ultimate Learning Machine Will Remake Our World. Basic Books, New York, NY.

Efron, B., and Hastie, T. (2016). Computer Age Statistical Inference. Cambridge University Press, New York, NY.

Freedman, D., Pisani, R., and Purves, R. (2007). Statistics. 4th ed. W. W. Norton &Company, New York, NY.

Hacking, I. (1990). The Taming of Chance (Ideas in Context). Cambridge University Press,Cambridge, UK.

Hoover, K. (2008). Causality in economics and econometrics. In The New Palgrave Dictionary of Economics (S. Durlauf and L. Blume, eds.), 2nd ed. Palgrave Macmillan,New York, NY.

Kleinberg, S. (2015). Why: A Guide to Finding and Using Causes. O’Reilly Media,Sebastopol, CA.

Losee, J. (2012). Theories of Causality: From Antiquity to the Present. Routledge, New York, NY.

Marcus, G. (July 30, 2017). Artifcial intelligence is stuck. Here’s how to move it forward.New York Times, SR6.

Mayer-Schönberger, V., and Cukier, K. (2013). Big Data: A Revolution That Will Transform How We Live, Work, and Think. Houghton Mifin Harcourt Publishing, New York, NY.

Morgan, S., and Winship, C. (2015). Counterfactuals and Causal Inference: Methods and Principles for Social Research (Analytical Methods for Social Research). 2nd ed.Cambridge University Press, New York, NY.

Mumford, S., and Anjum, R. L. (2014). Causation: A Very Short Introduction (Very Short Introductions). Oxford University Press, New York, NY.

Pearl, J. (1988). Probabilistic Reasoning in Intelligent Systems. Morgan Kaufmann, San Mateo, CA.

Pearl, J. (1994). A probabilistic calculus of actions. In Uncertainty in Artifcial Intelligence 10 (R. L. de Mantaras and D. Poole, eds.). Morgan Kaufmann, San Mateo, CA, 454–462.

Pearl, J. (1995). Causal diagrams for empirical research. Biometrika 82: 669–710.

Pearl, J. (2000a). Causality: Models, Reasoning, and Inference. Cambridge University Press, New York, NY.

Pearl, J. (2000b). Comment on A. P. Dawid’s Causal inference without counterfactuals.Journal of the American Statistical Association 95: 428–431.

Pearl, J. (2009). Causality: Models, Reasoning, and Inference. 2nd ed. Cambridge University Press, New York, NY.

Pearl, J. (2012). The causal foundations of structural equation modeling. In Handbook of Structural Equation Modeling (R. Hoyle, ed.). Guilford Press, New York, NY, 68–91.

Pearl, J. (2017). Advances in deep neural networks, at ACM Turing 50 Celebration.Available at: https: //www.youtube.com/watch?v=mFYM9j8bGtg (June 23, 2017).

Pearl, J., and Bareinboim, E. (2014). External validity: From do-calculus to transportability across populations. Statistical Science 29: 579–595.

Pearl, J., Glymour, M., and Jewell, N. (2016). Causal Inference in Statistics: A Primer.Wiley, New York, NY.

Provine, W. B. (1986). Sewall Wright and Evolutionary Biology. University of Chicago Press, Chicago, IL.

Salsburg, D. (2002). The Lady Tasting Tea: How Statistics Revolutionized Science in the Twentieth Century. Henry Holt and Company, LLC, New York, NY.

Spirtes, P., Glymour, C., and Scheines, R. (2000). Causation, Prediction, and Search. 2nd ed. MIT Press, Cambridge, MA.

Stigler, S. M. (1986). The History of Statistics: The Measurement of Uncertainty Before 1900. Belknap Press of Harvard University Press, Cambridge, MA.

Stigler, S. M. (1999). Statistics on the Table: The History of Statistical Concepts and Methods. Harvard University Press, Cambridge, MA.

Stigler, S. M. (2016). The Seven Pillars of Statistical Wisdom. Harvard University Press,Cambridge, MA.

Toulmin, S. (1961). Foresight and Understanding: An Enquiry into the Aims of Science.University of Indiana Press, Bloomington, IN.

Virgil. (29 bc). Georgics. Verse 490, Book 2.

第一章 因果关系之梯 注释书目

关于因果关系之梯的三个层级之间的区别,可以在Pearl(2000)的第1章中找到一个技术性的解释。

我们对因果关系之梯与人类认知发展之间的比较受到了Harari(2015)和Kind等人(2014)最近研究成果的启发。Kind的文章详细介绍了狮人雕像和发现它的地点。关于婴儿对因果关系的理解的发展的相关研究可在Weisberg和Gopnik(2013)中找到。

图灵测试最早是在1950年作为一个模仿游戏被提出的(Turing,1950)。Searl的“中文屋”论据出现在Searl(1980),并在此后的几年里被广泛讨论,见Russell和Norvig(2003)、Preston和Bishop(2002)、Pinker(1997)。使用模型修正来表示干预源自经济学家Trygeve Haavelmo(1943),相关的详细说明请参见Pearl(2015)。Spirtes、Glymour和Scheines(1993)给出了箭头删除的图示。Balke和Pearl(1994a,1994b)将其扩展到对反事实推理的模拟,如行刑队的例子所示。

Hitchcock(2016对概率因果论进行了全面总结。其他诸多关键思想见Reichenbach(1956)、Suppes(1970)、Cartwright(1983)、Spohn(2012。我对概率因果论和概率提高的分析见Pearl(2000;2009,第7.5节;2011)。

参考文献

Balke, A., and Pearl, J. (1994a). Counterfactual probabilities: Computational methods,bounds, and applications. In Uncertainty in Artifcial Intelligence 10 (R. L. de Mantaras and D. Poole, eds.). Morgan Kaufmann, San Mateo, CA, 46–54.

Balke, A., and Pearl, J. (1994b). Probabilistic evaluation of counter factual queries. In Proceedings of the Twelfth National Conference on Artifcial Intelligence, vol. 1. MIT Press, Menlo Park, CA, 230–237.

Cartwright, N. (1983). How the Laws of Physics Lie. Clarendon Press, Oxford, UK.

Haavelmo, T. (1943). The statistical implications of a system of simultaneous equations.

Econometrica 11: 1–12. Reprinted in D. F. Hendry and M. S. Morgan (Eds.), The Foundations of Econometric Analysis, Cambridge University Press, Cambridge, UK,477–490, 1995.

Harari, Y. N. (2015). Sapiens: A Brief History of Humankind. Harper Collins Publishers,New York, NY.

Hitchcock, C. (2016). Probabilistic causation. In Stanford Encyclopedia of Philosophy(Winter 2016) (E. N. Zalta, ed.). Metaphysics Research Lab, Stanford, CA.Available at: https: //stanford.library.sydney.edu.au/archives/win2016/entries/causationprobabilistic.

Kind, C. -J., Ebinger-Rist, N., Wolf, S., Beutelspacher, T., and Wehrberger, K. (2014).The smile of the Lion Man. Recent excavations in Stadel cave (Baden-Württemberg,south-western Germany) and the restoration of the famous upper palaeolithic fgurine.Quartär 61: 129–145.

Pearl, J. (2000). Causality: Models, Reasoning, and Inference. Cambridge University Press, New York, NY.

Pearl, J. (2009). Causality: Models, Reasoning, and Inference. 2nd ed. Cambridge University Press, New York, NY.

Pearl, J. (2011). The structural theory of causation. In Causality in the Sciences (P. M.Illari, F. Russo, and J. Williamson, eds.), chap.33. Clarendon Press, Oxford, UK, 697–727.

Pearl, J. (2015). Trygve Haavelmo and the emergence of causal calculus. Econometric Theory 31: 152–179. Special issue on Haavelmo centennial.

Pinker, S. (1997). How the Mind Works. W. W. Norton and Company, New York, NY.

Preston, J., and Bishop, M. (2002). Views into the Chinese Room: New Essays on Searle and Artifcial Intelligence. Oxford University Press, New York, NY.

Reichenbach, H. (1956). The Direction of Time. University of California Press, Berkeley,CA.

Russell, S. J., and Norvig, P. (2003). Artifcial Intelligence: A Modern Approach. 2nd ed.Prentice Hall, Upper Saddle River, NJ.

Searle, J. (1980). Minds, brains, and programs. Behavioral and Brain Sciences 3: 417–457.

Spirtes, P., Glymour, C., and Scheines, R. (1993). Causation, Prediction, and Search.Springer-Verlag, New York, NY.

Spohn, W. (2012). The Laws of Belief: Ranking Theory and Its Philosophical Applications.Oxford University Press, Oxford, UK.

Suppes, P. (1970). A Probabilistic Theory of Causality. North-Holl and Publishing Co.,Amsterdam, Netherlands.

Turing, A. (1950). Computing machinery and intelligence. Mind 59: 433–460.

Weisberg, D. S., and Gopnik, A. (2013). Pretense, counterfactuals, and Bayesian causal models: Why what is not real really matters. Cognitive Science 37: 1368–1381.

第二章 从海盗到豚鼠:因果推断的起源 注释书目

Galton在他的书(Galton,1869,1883,1889中对遗传和相关性的探索进行了描述,关于其事迹也被记录在Stigler(2012,2016中。

有关哈代—温伯格平衡的基本介绍,请参阅维基百科(2016a)。关于伽利略引文“E pur si muove”的来源,请参见维基百科(2016b)。Stigler(2012,第9页)中可以找到巴黎地下墓穴和Pearson对“人工混合”引起的相关性感到震惊的故事。

Wright寿比南山,他有幸在活着的时候看到了一本传记(Provine,1986的出版。Provine的传记到目前为止仍然是了解Wright职业生涯的最佳材料,我们特别推荐第5章,其内容是关于路径分析的。Crow的两部自传(Crow,1982,1990)也提供了一个非常好的解读视角。Wright(1920是关于路径图的一篇开创性论文;Wright(1921是一篇更全面的论述,也是豚鼠出生体重例子的来源。Wright(1983)是Wright对Karlin评论的回应,这篇评论写于他90多岁的时候。

Pearl(2000第5章和Bollen和Pearl(2013对经济学和社会科学中的路径分析的命运进行了叙述。Blalock(1964)、Duncan(1966和Goldberger(1972以极大的热情将Wright的思想介绍给了社会科学,但其理论基础没能很好地表达出来。10年后,当Freedman(1987向路径分析者提出挑战,要求他们解释如何对干预建模时,他们的热情消失了,而主要研究人员则退缩至将结构方程模型(SEMs视为统计分析中的一项活动。12位学者关于该问题的富有启发性的讨论与Freedman的文章刊载于《教育统计期刊》的同一期。

Pearl(2015描述了经济学家为何不愿意接受图示和结构符号。此项经济教育的不良后果则记录在Chen和Pearl(2013中。

在McGrayne(2011)中,人们对贝叶斯学派与频率派的辩论进行了丰富的阐述。更多的技术讨论见Efron(2013)和Lindley(1987)。

参考文献

Blalock, H., Jr. (1964). Causal Inferences in Nonexperimental Research. University of North Carolina Press, Chapel Hill, NC.

Bollen, K., and Pearl, J. (2013). Eight myths about causality and structural equation models. In Handbook of Causal Analysis for Social Research (S. Morgan, ed.).Springer, Dordrecht, Netherlands, 301–328.

Chen, B., and Pearl, J. (2013). Regression and causation: A critical examination of econometrics textbooks. Real-World Economics Review 65: 2–20.

Crow, J. F. (1982). Sewall Wright, the scientist and the man. Perspectives in Biology and Medicine 25: 279–294.

Crow, J. F. (1990). Sewall Wright’s place in twentieth-century biology. Journal of the History of Biology 23: 57–89.

Duncan, O. D. (1966). Path analysis. American Journal of Sociology 72: 1–16.

Efron, B. (2013). Bayes’ theorem in the 21st century. Science 340:1177–1178.

Freedman, D. (1987). As others see us: A case study in path analysis (with discussion).Journal of Educational Statistics 12: 101–223.

Galton, F. (1869). Hereditary Genius. Macmillan, London, UK.

Galton, F. (1883). Inquiries into Human Faculty and Its Development. Macmillan, London,UK.

Galton, F. (1889). Natural Inheritance. Macmillan, London, UK.

Goldberger, A. (1972). Structural equation models in the social sciences. Econometrica:Journal of the Econometric Society 40: 979–1001.

Lindley, D. (1987). Bayesian Statistics: A Review. CBMS-NSF Regional Conference Series in Applied Mathematics (Book 2). Society for Industrial and Applied Mathematics,Philadelphia, PA.

McGrayne, S. B. (2011). The Theory That Would Not Die. Yale University Press, New Haven, CT.

Pearl, J. (2000). Causality: Models, Reasoning, and Inference. Cambridge University Press, New York, NY.

Pearl, J. (2015). Trygve Haavelmo and the emergence of causal calculus. Econometric Theory 31: 152–179. Special issue on Haavelmo centennial.

Provine, W. B. (1986). Sewall Wright and Evolutionary Biology. University of Chicago Press, Chicago, IL.

Stigler, S. M. (2012). Studies in the history of probability and statistics, L: Karl Pearson and the rule of three. Biometrika 99: 1–14.

Stigler, S. M. (2016). The Seven Pillars of Statistical Wisdom. Harvard University Press,Cambridge, MA.

Wikipedia. (2016a). Hardy-Weinberg principle. Available at: https://en.wikipedia.org/wiki/Hardy-Weinberg-principle (last edited: October 2, 2016).

Wikipedia. (2016b). Galileo Galilei. Available at: https://en.wikipedia.org/wiki/Galileo_Galilei (last edited: October 6, 2017).

Wright, S. (1920). The relative importance of heredity and environment in determining the piebald pattern of guinea-pigs. Proceedings of the National Academy of Sciences of the United States of America 6: 320–332.

Wright, S. (1921). Correlation and causation. Journal of Agricultural Research 20: 557–585.

Wright, S. (1983). On “Path analysis in genetic epidemiology: A critique.” American Journal of Human Genetics 35: 757–768.

第三章 从证据到因:当贝叶斯牧师遇见福尔摩斯先生 注释书目

Lindley(2014与Pearl、Glymour和Jewell(2016对贝叶斯法则和贝叶斯思维进行了初步介绍。对不确定性相互矛盾的表示的辩论见Pearl(1988,另见下面给出的大量参考文献。

我们的乳房X光检查例子的数据主要源于乳腺癌监测联合会(BCSC,2009)和美国预防服务工作组(USPSTF,2016年)提供的信息,仅供参考。

“贝叶斯网络”于1985年得名(Pearl,1985),并作为自我激活记忆的模型首次面向学界公开。专家系统的应用紧跟循环网络信念更新算法的发展(Pearl,1986;Lauritzen和Spiegelhalter,1988)。

d分离性的概念将图中的路径阻断与数据中的依存关系联系起来,其根植于拟图理论(Pearl和Paz,1985。该理论揭示了图和概率的共同属性(并因此得名),并解释了为什么这两个看似不相关的数学对象可以在许多方面相互支持。另见维基百科“拟图”(graphoid)。

在飞机场等行李的有趣例子可在Conrady和Jouffe(2015,第4章)中找到。

马来西亚航空公司17号航班的空难在多家媒体上都有详尽的报道,请参阅Clark和Kramer(2015年10月14日)了解事故发生一年后调查的最新情况。Wiegerinck、Burgers和Kappen(2013)描述了波拿巴的工作原理。关于17号航班遇难者身份识别的更多细节,包括图3.7所示的谱系,来自W. Burgers与D. Mackenzie的私人通信(2016年8月24日),以及D. Mackenzie对W. Burgers和B. Kappen的电话采访(2016年8月23日)。

关于turbo码和低密度校验码的复杂而迷人的故事从未有人以真正通俗易懂的方式对公众讲述过,但几个不错的学习起点是Costello和Forney(2007),以及Hardesty(2010a,2010b)。通过信念传播算法实现turbo编码的关键工作来自McElice、David和Cheng(1998)。

高效编码的开发仍然是无线通信的战场,Carlton(2016)研究了目前“5G”手机的竞争对手(将于21世纪20年代推出)。

参考文献

Breast Cancer Surveillance Consortium (BCSC). (2009). Performance measures for 1,838,372 screening mammography examinations from 2004 to 2008 by age. Available at: http://www.bcsc-research.org/statistics/performance/screening/2009/perf_age.html(accessed October 12, 2016).

Carlton, A. (2016). Surprise! Polar codes are coming in from the cold. Computerworld.Available at: https://www.computerworld.com/article/3151866/mobile-wireless/surprise-polar-codes-are-coming-in-from-the-cold.html (posted December 22, 2016).

Clark, N., and Kramer, A. (October 14, 2015). Malaysia Airlines Flight 17 most likely hit by Russian-made missile, inquiry says. New York Times.

Conrady, S., and Jouffe, L. (2015). Bayesian Networks and Bayesia Lab: A Practical Introduction for Researchers. Bayesia USA, Franklin, TN.

Costello, D. J., and Forney, G. D., Jr. (2007). Channel coding: The road to channel capacity. Proceedings of IEEE 95: 1150–1177.

Hardesty, L. (2010a). Explained: Gallager codes. MIT News. Available at: http://news.mit.edu/2010/gallager-codes-0121 (posted:January 21, 2010).

Hardesty, L. (2010b). Explained: The Shannon limit. MIT News. Available at: http://news.mit.edu/2010/explained-shannon-0115 (posted January 19, 2010).

Lauritzen, S., and Spiegelhalter, D. (1988). Local computations with probabilities on graphical structures and their application to expert systems (with discussion). Journal of the Royal Statistical Society, Series B 50: 157–224.

Lindley, D. V. (2014). Understanding Uncertainty. Rev. ed. John Wiley and Sons,Hoboken, NJ.

McEliece, R. J., David, J. M., and Cheng, J. (1998). Turbo decoding as an instance of Pearl’s “belief propagation” algorithm. IEEE Journal on Selected Areas in Communications 16: 140–152.

Pearl, J. (1985). Bayesian networks: A model of self-activated memory for evidential reasoning. In Proceedings, Cognitive Science Society (CSS-7). UCLA Computer Science Department, Irvine, CA.

Pearl, J. (1986). Fusion, propagation, and structuring in belief networks. Artifcial Intelligence 29: 241–288.

Pearl, J. (1988). Probabilistic Reasoning in Intelligent Systems. Morgan Kaufmann, San Mateo, CA.

Pearl, J., Glymour, M., and Jewell, N. (2016). Causal Inference in Statistics: A Primer.Wiley, New York, NY.

Pearl, J., and Paz, A. (1985). GRAPHOIDS: A graph-based logic for reasoning about relevance relations. Tech. Rep. 850038 (R-53-L).Computer Science Department,University of California, Los Angeles. Short version in B. DuBoulay, D. Hogg, and L. Steels (Eds.) Advances in Artifcial Intelligence—II, Amsterdam, North Holland,357–363, 1987.

US Preventive Services Task Force (USPSTF) (2016). Final recommendation statement:Breast cancer: Screening. Available at:https://www.uspreventiveservicestaskforce.org/Page/Document/RecommendationStatementFinal/breast-cancer-screening1 (updated:January 2016).

Wikipedia. (2018). Graphoid. Available at: https://en.wikipedia.org/wiki/Graphoid (last edited: January 8, 2018).

Wiegerinck, W., Burgers, W., and Kappen, B. (2013). Bayesian networks, introduction and practical applications. In Handbook on Neural Information Processing (M. Bianchini,M. Maggini, and L. C. Jain, eds.). Intelligent Systems Reference Library (Book 49).Springer, Berlin, Germany, 401–431.

第四章 混杂和去混杂:或者,消灭潜伏变量 注释书目

丹尼尔的故事经常被引用为第一个对照试验,见Lilienfeld(1982)或Stigler(2016)。檀香山步行研究的结果见Hakim(1998)。

Fisher Box关于“对自然的巧妙询问”的长篇引文来自其撰写的关于她父亲的一本优秀传记(Box,1978,第6章)。Fisher本人也把试验写成了与自然的对话,见Stigler(2016。因此,我相信我们可以说她的引文几乎完全来自Fisher本人,只是表达得更优美。

一篇接一篇地阅读Weinberg关于混淆的论文(Weinberg,1993;Howards等人,2012)很有意思。它们就像混淆历史的两张快照,一张是在因果图广泛传播之前拍摄的,另一张则拍摄于20年后,其中我们使用因果图重新审视了相同的例子。Forbes关于哮喘和吸烟的因果关系网的复杂图参见Williamson等人(2014)。

Morabia的“混杂的经典流行病学定义”可以在Morabia(2011找到。David Cox的引文来自Cox(1992,第66–67页)。关于混杂历史的其他文献包括Greenland和Robins(2009以及维基百科(2016)。

Pearl(1993提出了消除混杂偏倚的后门标准及后门调整公式。它对流行病学的影响可以通过Greenland、Pearl和Robins(1999来了解。对序贯干预和其他存在细微差别的扩展应用在Pearl(2000,2009中得到了发展,在Pearl、Glymour和Jewell(2016中有更细致的描述。Tikka和Karvanen(2017提供了使用do演算计算因果效应的软件。

考虑到自那时以来对混杂理解的广泛发展,包括因果图的出现(Greenland和Robins,2009),Greenland和Robins(1986)的论文在1/4个世纪后被作者收回重新阐述了一遍。

参考文献

Box, J. F. (1978). R. A. Fisher: The Life of a Scientist. John Wiley and Sons, New York,NY.

Cox, D. (1992). Planning of Experiments. Wiley-Interscience, New York, NY.

Greenland, S., Pearl, J., and Robins, J. (1999). Causal diagrams for epidemiologic research.Epidemiology 10: 37–48.

Greenland, S., and Robins, J. (1986). Identifability, exchangeability,and epidemiological confounding. International Journal of Epidemiology 15: 413–419.

Greenland, S., and Robins, J. (2009). Identifability, exchangeability,and confounding revisited. Epidemiologic Perspectives & Innovations 6. doi:10.1186/1742-5573-6-4.

Hakim, A. (1998). Effects of walking on mortality among nonsmoking retired men. New England Journal of Medicine 338: 94–99.

Hernberg, S. (1996). Signifcance testing of potential confounders and other properties of study groups—Misuse of statistics. Scandinavian Journal of Work, Environment and Health 22: 315–316.

Howards, P. P., Schisterman, E. F., Poole, C., Kaufman, J. S.,and Weinberg, C. R. (2012).“Toward a clearer defnition of confounding” revisited with directed acyclic graphs.American Journal of Epidemiology 176: 506–511.

Lilienfeld, A. (1982). Ceteris paribus: The evolution of the clinical trial. Bulletin of the History of Medicine 56: 1–18.

Morabia, A. (2011). History of the modern epidemiological concept of confounding.Journal of Epidemiology and Community Health 65: 297–300.

Pearl, J. (1993). Comment: Graphical models, causality, and intervention. Statistical Science 8: 266–269.

Pearl, J. (2000). Causality: Models, Reasoning, and Inference. Cambridge University Press, New York, NY.

Pearl, J. (2009). Causality: Models, Reasoning, and Inference. 2nd ed. Cambridge University Press, New York, NY.

Pearl, J., Glymour, M., and Jewell, N. (2016). Causal Inference in Statistics: A Primer.Wiley, New York, NY.

Stigler, S. M. (2016). The Seven Pillars of Statistical Wisdom. Harvard University Press,Cambridge, MA.

Tikka, J., and Karvanen, J. (2017). Identifying causal effects with the R Package causaleffect. Journal of Statistical Software 76, no. 12. doi:10.18637/jss.r076.i12.

Weinberg, C. (1993). Toward a clearer defnition of confounding. American Journal of Epidemiology 137: 1–8.

Wikipedia. (2016). Confounding. Available at: https://en.wikipedia.org/wiki/Confounding(accessed: September 16, 2016).

Williamson, E., Aitken, Z., Lawrie, J., Dharmage, S., Burgess, H.,and Forbes, A. (2014).Introduction to causal diagrams for confounder selection. Respirology 19: 303–311.

第五章 烟雾缭绕的争论:消除迷雾,澄清事实 注释书目

Brandt(2007和Proctor(2012a这两本书包含了读者想要了解的关于吸烟与肺癌辩论的所有信息,除非你还想阅读烟草公司后来公布的实际文件(可在线获取)。20世纪50年代关于吸烟与癌症之关系争论的简短调查见Salsburg(2002,第18章)、Parascandola(2004和Proctor(2012b)。Stolley(1991研究了R. A.Fisher在此争论中的独特作用,Greenhouse(2009评论了Jerome Cornfield的发现的重要性。惊世一枪是Doll和Hill(1950,这是第一次对吸烟与肺癌的因果关系的讨论,虽然讨论的是技术性问题,但不失为一篇经典科学论文。

关于美国卫生局局长委员会的故事和Hill因果关系指南的出现,见Blackburn和Labarthe(2012)和Morabia(2013)。Hill对他的标准的描述可以在Hill(1965)中找到。

Lilienfeld(2007是亚伯与雅克故事的来源,我们以此开始了这一章。

VanderWeele(2014与Hernández-Díaz、Schisterman和Hernán(2006使用因果图解决了出生体重悖论。两篇有趣的与之相关的文章是Wilcox(2001,2006,分别是作者在了解因果图之前和之后写的,他在后一篇文章中的兴奋显而易见。

对癌症死亡率和吸烟的最新统计数据和历史趋势感兴趣的读者可以参考询美国卫生与公众服务部(USDHS,2014)、美国癌症协会(2017)和Wingo(2003)。

参考文献

American Cancer Society. (2017). Cancer facts and fgures. Available at: https://www.cancer.org/research/cancer-facts-statistics.html(posted: February 19, 2015).

Blackburn, H., and Labarthe, D. (2012). Stories from the evolution of guidelines for causal inference in epidemiologic associations:1953–1965. American Journal of Epidemiology 176: 1071–1077.

Brandt, A. (2007). The Cigarette Century. Basic Books, New York,NY.

Doll, R., and Hill, A. B. (1950). Smoking and carcinoma of the lung. British Medical Journal 2: 739–748.

Greenhouse, J. (2009). Commentary: Cornfeld, epidemiology, and causality. International Journal of Epidemiology 38: 1199–1201.

Hernández-Díaz, S., Schisterman, E., and Hernán, M. (2006). The birth weight “paradox”uncovered? American Journal of Epidemiology 164: 1115–1120.

Hill, A. B. (1965). The environment and disease: Association or causation? Journal of the Royal Society of Medicine 58: 295–300.

Lilienfeld, A. (2007). Abe and Yak: The interactions of Abraham M.Lilienfeld and Jacob Yerushalmy in the development of modern epidemiology (1945–1973). Epidemiology 18: 507–514.

Morabia, A. (2013). Hume, Mill, Hill, and the sui generis epidemiologic approach to causal inference. American Journal of Epidemiology 178: 1526–1532.

Parascandola, M. (2004). Two approaches to etiology: The debate over smoking and lung cancer in the 1950s. Endeavour 28: 81–86.

Proctor, R. (2012a). Golden Holocaust: Origins of the Cigarette Catastrophe and the Case for Abolition. University of California Press, Berkeley, CA.

Proctor, R. (2012b). The history of the discovery of the cigarette-lung cancer link:Evidentiary traditions, corporate denial, and global toll. Tobacco Control 21: 87–91.

Salsburg, D. (2002). The Lady Tasting Tea: How Statistics Revolutionized Science in the Twentieth Century . Henry Holt and Company, New York, NY.

Stolley, P. (1991). When genius errs: R. A. Fisher and the lung cancer controversy.American Journal of Epidemiology 133: 416–425.

US Department of Health and Human Services (USDHHS). (2014).The health consequences of smoking—50 years of progress: A report of the surgeon general.USDHHS and Centers for Disease Control and Prevention, Atlanta, GA.

VanderWeele, T. (2014). Commentary: Resolutions of the birthweight paradox: Competing explanations and analytical insights. International Journal of Epidemiology 43: 1368–1373.

Wilcox, A. (2001). On the importance—and the unimportance—of birthweight.International Journal of Epidemiology 30: 1233–1241.

Wilcox, A. (2006). The perils of birth weight—A lesson from directed acyclic graphs.American Journal of Epidemiology 164: 1121–1123.

Wingo, P. (2003). Long-term trends in cancer mortality in the United States, 1930–1998.Cancer 97: 3133–3275.

第六章 大量的悖论! 注释书目

蒙提·霍尔悖论在许多概率论入门书(例如,Grinstead和Snell,1998,第136页;Lindley,2014,第201页)中都可以看到。Pearl(1988,第58–62页)使用等效的“三个囚犯困境”演示了非贝叶斯法则的不足。

Tierney(1991年7月21日)和Crockett(2015讲述了沃斯·莎凡特专栏关于蒙提·霍尔悖论的精彩故事;Crockett还发表了沃斯·莎凡特从所谓的专家那里收到的其他一些或有趣或尴尬的评论。Tierney的文章讲述了蒙提·霍尔自己对这场争论的看法,这是一个有趣的体现人类兴趣的视角!

Pearl(2009,第174–182页)对辛普森悖论的历史渊源做了一个宏观的描述,其中包括统计学家和哲学家在不援引因果关系的情况下解决这一悖论的许多尝试。Pearl(2014提供了一份针对教育工作者的最新报告。

Savage(2009)、Julious和Mullee(1994以及Appleton、French和Vanderpump(1996给出了文本中提到的辛普森悖论的三个现实例子(分别与棒球、肾结石和吸烟有关)。

Savage的确凿性原则(Savage,1954在Pearl(2016b中得到了进一步的处理,其修正后的因果版本在Pearl(2009,第181–182页)中被推导出来。

罗德悖论(Lord,1967)的不同版本在Glymour(2006),Hernández-Díaz、Schisterman和Hernán(2006),Senn(2006),Wainer(1991)中有所介绍。你也可以在Pearl(2016a)中找到更全面的分析。

本章不包括援引反事实的悖论,但它们同样有趣,有关例子请参阅Pearl(2013)。

参考文献

Appleton, D., French, J., and Vanderpump, M. (1996). Ignoring a covariate: An example of Simpson’s paradox. American Statistician 50: 340–341.

Crockett, Z. (2015). The time everyone “corrected” the world’s smartest woman.Priceonomics. Available at: http://priceonomics.com/the-time-everyone-corrected-theworlds-smartest (posted: February 19, 2015).

Glymour, M. M. (2006). Using causal diagrams to understand common problems in social epidemiology. In Methods in Social Epidemiology. John Wiley and Sons, San Francisco, CA, 393–428.

Grinstead, C. M., and Snell, J. L. (1998). Introduction to Probability. 2nd rev. ed. American Mathematical Society, Providence, RI.

Hernández-Díaz, S., Schisterman, E., and Hernán, M. (2006). The birth weight “paradox”uncovered? American Journal of Epidemiology 164: 1115–1120.

Julious, S., and Mullee, M. (1994). Confounding and Simpson’s paradox. British Medical Journal 309: 1480–1481.

Lindley, D. V. (2014). Understanding Uncertainty. Rev. ed. John Wiley and Sons,Hoboken, NJ.

Lord, F. M. (1967). A paradox in the interpretation of group comparisons. Psychological Bulletin 68: 304–305.

Pearl, J. (1988). Probabilistic Reasoning in Intelligent Systems. Morgan Kaufmann, San Mateo, CA.

Pearl, J. (2009). Causality: Models, Reasoning, and Inference. 2nd ed.Cambridge University Press, New York, NY.

Pearl, J. (2013). The curse of free-will and paradox of inevitable regret. Journal of Causal Inference 1: 255–257.

Pearl, J. (2014). Understanding Simpson’s paradox. American Statistician 88: 8–13.

Pearl, J. (2016a). Lord’s paradox revisited—(Oh Lord! Kumbaya!). Journal of Causal Inference 4. doi:10.1515/jci-2016-0021.

Pearl, J. (2016b). The sure-thing principle. Journal of Causal Inference 4: 81–86.

Savage, L. (1954). The Foundations of Statistics. John Wiley and Sons, New York, NY.

Savage, S. (2009). The Flaw of Averages: Why We Underestimate Risk in the Face of Uncertainty. John Wiley and Sons, Hoboken, NJ.

Senn, S. (2006). Change from baseline and analysis of covariance revisited. Statistics in Medicine 25: 4334–4344.

Simon, H. (1954). Spurious correlation: A causal interpretation. Journal of the American Statistical Association 49: 467–479.

Tierney, J. (July 21, 1991). Behind Monty Hall’s doors: Puzzle, debate and answer? New York Times.

Wainer, H. (1991). Adjusting for differential base rates: Lord’s paradox again.Psychological Bulletin 109: 147–151.

第七章 超越统计调整:征服干预之峰 注释书目

基于Tian的c分解,Tian和Pearl(2002)首次报告了后门和前门调整的扩展方法。接下来是Shpitser的do演算的算法化(Shpitser和Pearl,2006a),然后是Shpitser和Pearl(2006b)以及Huang和Valtorta(2006)的完备性证明结果。

读者中的经济学研究者应该注意到了,对图分析工具招致的文化性阻力(Heckman和Pinto,2015;Imbens和Rubin,2015)并非所有经济学家都认同。例如,White和Chalak(2009)将 do演算推广并应用于涉及平衡和学习的经济系统。最近出版的社会和行为科学方面的教科书,Morgan和Winship(2007)及Kline(2016),进一步向年轻的研究者发出了这样的信号:文化正统主义,就如同17世纪对望远镜的恐惧,在科学界是不会长久存在的。

约翰·斯诺对霍乱的长期调查很少受到重视,在《柳叶刀》上刊登的关于他的一段讣告甚至没有提到这一点。值得注意的是,《英国医学杂志》在155年后“修正”了这段讣告(Hempel,2013)。更多关于斯诺的传记材料,见Hill(1955)、Cameron和Jones(1983)。对于存在未观测的混淆因子这种情况,Glynn和Kashin(2018)是从经验上演示前门调节优于后门调节的最早的论文之一。Freedman对“吸烟 → 焦油沉积 → 肺癌”例子的批评可以在Freedman(2010)的一章中找到,其标题为“关于为因果关系指定图模型”。

关于工具变量的介绍可以在Greenland(2000)和许多计量经济学教科书(例如,Bowden和Turkington,1984;Wooldridge,2013)中找到。

Brito和Pearl(2002引入了广义的工具变量,它扩展了本书给出的经典定义。

DAGitty程序(可在线访问http://www.dagitty.net/dags.html允许用户搜索图中的广义工具变量,并报告生成的被估量(Textor、Hardt和Knüppel,2011。另一个基于图的决策软件包是BayesiaLab(www.bayesia.com)。

Pearl(2009第8章对工具变量估计的边界进行了详细研究,并将结果应用于未履行问题。Imbens(2010提倡并讨论了局部平均处理效应(LATE逼近。

参考文献

Bareinboim, E., and Pearl, J. (2012). Causal inference by surrogate experiments:z-identifability. In Proceedings of the Twenty-Eighth Conference on Uncertainty in Artifcial Intelligence (N. de Freitas and K. Murphy, eds.). AUAI Press, Corvallis, OR.

Bowden, R., and Turkington, D. (1984). Instrumental Variables.Cambridge University Press, Cambridge, UK.

Brito, C., and Pearl, J. (2002). Generalized instrumental variables. In Uncertainty in Artifcial Intelligence, Proceedings of the Eighteenth Conference (A. Darwiche and N.Friedman, eds.). Morgan Kaufmann, San Francisco, CA, 85–93.

Cameron, D., and Jones, I. (1983). John Snow, the Broad Street pump,and modern epidemiology. International Journal of Epidemiology 12: 393–396.

Cox, D., and Wermuth, N. (2015). Design and interpretation of studies: Relevant concepts from the past and some extensions. Observational Studies 1. Available at: https://arxiv.org/pdf/1505.02452.pdf.

Freedman, D. (2010). Statistical Models and Causal Inference: A Dialogue with the Social Sciences. Cambridge University Press, New York, NY.

Glynn, A., and Kashin, K. (2018). Front-door versus back-door adjustment with unmeasured confounding: Bias formulas for frontdoor and hybrid adjustments. Journal of the American Statistical Association. To appear.

Greenland, S. (2000). An introduction to instrumental variables for epidemiologists.International Journal of Epidemiology 29: 722–729.

Heckman, J. J., and Pinto, R. (2015). Causal analysis after Haavelmo.Econometric Theory 31: 115–151.

Hempel, S. (2013). Obituary: John Snow. Lancet 381: 1269–1270.

Hill, A. B. (1955). Snow—An appreciation. Journal of Economic Perspectives 48: 1008–1012.

Huang, Y., and Valtorta, M. (2006). Pearl’s calculus of intervention is complete. In Proceedings of the Twenty-Second Conference on Uncertainty in Artifcial Intelligence (R. Dechter and T. Richardson, eds.). AUAI Press, Corvallis, OR, 217–224.

Imbens, G. W. (2010). Better LATE than nothing: Some comments on Deaton (2009) and Heckman and Urzua (2009). Journal of Economic Literature 48: 399–423.

Imbens, G. W., and Rubin, D. B. (2015). Causal Inference for Statistics, Social, and Biomedical Sciences: An Introduction. Cambridge University Press, Cambridge, MA.

Kline, R. B. (2016). Principles and Practice of Structural Equation Modeling. 3rd ed.Guilford, New York, NY.

Morgan, S., and Winship, C. (2007). Counterfactuals and Causal Inference: Methods and Principles for Social Research (Analytical Methods for Social Research). Cambridge University Press, New York, NY.

Pearl, J. (2009). Causality: Models, Reasoning, and Inference. 2nd ed. Cambridge University Press, New York, NY.

Pearl, J. (2013). Reflections on Heckman and Pinto’s “Causal analysis after Haavelmo.”Tech. Rep. R-420. Department of Computer Science, University of California, Los Angeles, CA. Working paper.

Pearl, J. (2015). Indirect confounding and causal calculus (on three papers by Cox and Wermuth). Tech. Rep. R-457. Department of Computer Science, University of California, Los Angeles, CA.

Shpitser, I., and Pearl, J. (2006a). Identifcation of conditional interventional distributions.In Proceedings of the Twenty-Second Conference on Uncertainty in Artifcial Intelligence (R. Dechter and T. Richardson, eds.). AUAI Press, Corvallis, OR, 437–444.

Shpitser, I., and Pearl, J. (2006b). Identifcation of joint interventional distributions in recursive semi-Markovian causal models. In Proceedings of the Twenty-First National Conference on Artifcial Intelligence. AAAI Press, Menlo Park, CA, 1219–1226.

Stock, J., and Trebbi, F. (2003). Who invented instrumental variable regression? Journal of Economic Perspectives 17: 177–194.

Textor, J., Hardt, J., and Knüppel, S. (2011). DAGitty: A graphical tool for analyzing causal diagrams. Epidemiology 22: 745.

Tian, J., and Pearl, J. (2002). A general identifcation condition for causal effects. In Proceedings of the Eighteenth National Conference on Artifcial Intelligence. AAAI Press/MIT Press, Menlo Park, CA, 567–573.

Wermuth, N., and Cox, D. (2008). Distortion of effects caused by indirect confounding.Biometrika 95: 17–33. (See Pearl [2009, Chapter 4] for a general solution.)

Wermuth, N., and Cox, D. (2014). Graphical Markov models: Overview. ArXiv:1407.7783.

White, H., and Chalak, K. (2009). Settable systems: An extension of Pearl’s causal model with optimization, equilibrium and learning. Journal of Machine Learning Research 10: 1759–1799.

Wooldridge, J. (2013). Introductory Econometrics: A Modern Approach. 5th ed. SouthWestern, Mason, OH.

第八章 反事实:探索关于假如的世界 注释书目

Balke和Pearl(1994a,1994b介绍了反事实作为结构方程衍生物的定义,并将其用于估计法律语境中因果关系的概率。该框架与Rubin和Lewis提出并发展的框架之间的关系在Pearl(2000,第7章)中有详细讨论,其中,它们被证明在逻辑上是等价的:在一个框架中可以解决的问题将在另一个框架中产生相同的解。

最近出版的社会科学书籍(如Morgan和Winship,2015)和健康科学书籍(如Vanderweele,2015采用了我们在本书中所追求的混合的图—反事实方法。关于线性反事实的内容是以Pearl(2009,第389–391页)为基础的,该章节还提供了对第258页脚注中提出的问题的解决方案。我们对参与者处理效应(ETT的讨论建立在Shpitser和Pearl(2009的基础上。

Greenland(1999详细讨论了归因的法律问题以及因果关系的概率,Greenland是此类问题的反事实解决方法的先驱。我们对 PN、PS 和 PNS 的处理基于Tian和Pearl(2000及Pearl(2009,第9章)。Pearl、Glymour和Jewell(2016提出了一种更细致的反事实归因方法,还包括一个用于估计的工具包。Halpern(2016对实际因果关系进行了颇具技术性的形式处理。

潜在结果的研究者经常使用匹配技术来估计因果效应(Sekhon,2007),尽管他们通常忽略了我们在“学历—工作经验—工资”示例中展示的陷阱。通过对Mohan和Pearl(2014)的分析,我认识到应在因果建模的背景下看待缺失数据问题。

Cowles(2016和Reid(1998讲述了Neyman在伦敦动荡岁月的经历,包括关于Fisher和木制模型的逸事。Greiner(2008是对法律中“若非因果关系”的一个历史性的、实质性的介绍。Allen(2003),、Stott等人(2013)、Trenberth(2012)和Hannart等人(2016解决了将异常天气归因于气候变化的问题,Hannart特别提出了充要概率的概念,使主题更加清晰。

参考文献

Allen, M. (2003). Liability for climate change. Nature 421: 891–892.

Balke, A., and Pearl, J. (1994a). Counterfactual probabilities: Computational methods,bounds, and applications. In Uncertainty in Artifcial Intelligence 10 (R. L. de Mantaras and D. Poole, eds.).Morgan Kaufmann, San Mateo, CA, 46–54.

Balke, A., and Pearl, J. (1994b). Probabilistic evaluation of counterfactual queries. In Proceedings of the Twelfth National Conference on Artifcial Intelligence, vol. 1. MIT Press, Menlo Park,CA, 230–237.

Cowles, M. (2016). Statistics in Psychology: An Historical Perspective. 2nd ed. Routledge,New York, NY.

Duncan, O. (1975). Introduction to Structural Equation Models. Academic Press, New York, NY.

Freedman, D. (1987). As others see us: A case study in path analysis(with discussion).Journal of Educational Statistics 12: 101–223.

Greenland, S. (1999). Relation of probability of causation, relative risk, and doubling dose:A methodologic error that has become a social problem. American Journal of Public Health 89: 1166–1169.

Greiner, D. J. (2008). Causal inference in civil rights litigation. Harvard Law Review 81:533–598.

Haavelmo, T. (1943). The statistical implications of a system of simultaneous equations.Econometrica 11: 1–12. Reprinted in D.F.Hendry and M. S. Morgan (Eds.), The Foundations of Econometric Analysis, Cambridge University Press, Cambridge, UK,477–490, 1995.

Halpern, J. (2016). Actual Causality. MIT Press, Cambridge, MA.

Hannart, A., Pearl, J., Otto, F., Naveu, P., and Ghil, M. (2016).Causal counterfactual theory for the attribution of weather and climate-related events. Bulletin of the American Meteorological Society (BAMS) 97: 99–110.

Holland, P. (1986). Statistics and causal inference. Journal of the American Statistical Association 81: 945–960.

Hume, D. (1739). A Treatise of Human Nature. Oxford University Press, Oxford, UK.Reprinted 1888.

Hume, D. (1748). An Enquiry Concerning Human Understanding.Reprinted Open Court Press, LaSalle, IL, 1958.

Joffe, M. M., Yang, W. P., and Feldman, H. I. (2010). Selective ignorability assumptions in causal inference. International Journal of Biostatistics 6. doi:10.2202/1557-4679.1199. Lewis, D. (1973a). Causation. Journal of Philosophy 70: 556–567. Reprinted with postscript in D. Lewis, Philosophical Papers, vol. 2, Oxford University Press, New York, NY, 1986.

Lewis, D. (1973b). Counterfactuals. Harvard University Press, Cambridge, MA.

Lewis, M. (2016). The Undoing Project: A Friendship That Changed Our Minds. W. W.Norton and Company, New York, NY.

Mohan, K., and Pearl, J. (2014). Graphical models for recovering probabilistic and causal queries from missing data. Proceedings of Neural Information Processing 27: 1520–1528.

Morgan, S., and Winship, C. (2015). Counterfactuals and Causal Inference: Methods and Principles for Social Research (Analytical Methods for Social Research). 2nd ed.Cambridge University Press, New York, NY.

Neyman, J. (1923). On the application of probability theory to agricultural experiments.Essay on principles. Section 9. Statistical Science 5: 465–480.

Pearl, J. (2000). Causality: Models, Reasoning, and Inference. Cambridge University Press, New York, NY.

Pearl, J. (2009). Causality: Models, Reasoning, and Inference. 2nd ed. Cambridge University Press, New York, NY.

Pearl, J., Glymour, M., and Jewell, N. (2016). Causal Inference in Statistics: A Primer.Wiley, New York, NY.

Reid, C. (1998). Neyman. Springer-Verlag, New York, NY.

Rubin, D. (1974). Estimating causal effects of treatments in randomized and nonrandomized studies. Journal of Educational Psychology 66: 688–701.

Sekhon, J. (2007). The Neyman-Rubin model of causal inference and estimation via matching methods. In The Oxford Handbook of Political Methodology (J. M. BoxSteffensmeier, H. E. Brady,and D. Collier, eds.). Oxford University Press, Oxford, UK. Shpitser, I., and Pearl, J. (2009). Effects of treatment on the treated:Identifcation and generalization. In Proceedings of the TwentyFifth Conference on Uncertainty in Artifcial Intelligence. AUAI Press, Montreal, Quebec, 514–521.

Stott, P. A., Allen, M., Christidis, N., Dole, R. M., Hoerling, M.,Huntingford, C., Pardeep Pall, J. P., and Stone, D. (2013). Attribution of weather and climate-related events. In Climate Science for Serving Society: Research, Modeling, and Prediction Priorities (G.R. Asrar and J. W. Hurrell, eds.).Springer, Dordrecht,Netherlands, 449–484.

Tian, J., and Pearl, J. (2000). Probabilities of causation: Bounds and identifcation. Annals of Mathematics and Artifcial Intelligence 28: 287–313.

Trenberth, K. (2012). Framing the way to relate climate extremes to climate change.Climatic Change 115: 283–290.

VanderWeele, T. (2015). Explanation in Causal Inference: Methods for Mediation and Interaction. Oxford University Press, New York, NY.

第九章 中介:寻找隐藏的作用机制 注释书目

有几本书专门讨论了中介问题。最新的参考文献VanderWeele(2015)、Mackinnon(2008)也包含许多例子。Pearl(2014)和Kline(2015)描述了从Baron和Kenny(1986)的统计方法到基于反事实的因果中介方法的戏剧性转变。McDonald的引言(“……从头开始”)取材于McDonald(2001)。

Robins和Greenland(1992对自然直接效应和自然间接效应进行了概念化,并认为其存在问题。后来,它们在Pearl(2001中得到了正式化和合法化,从而形成了中介公式。

除了VanderWeele(2015)的综述外,中介分析的新结果和新应用可参阅De Stavola等人(2015),Imai、Keele和Yamamoto(2010),Muthén和Asparouhov(2015)。Shpitser(2013)提供了估算图示中任意路径特定效应的一般标准。

中介谬误和“以中介物为条件”的谬误在Pearl(1998),以及Cole和Hernán(2002)中得到了说明。根据Rubin(2005),Fisher支持这个谬误,而Rubin(2004)则视中介分析为“欺骗性的”而将之摈弃。

Lewis(1972和Ceglowski(2010讲述了坏血病的治疗是如何“失传”的惊人故事。King、Montañez Ramírez和Wertheimer(1996讲述了Barbara Burks的故事;来自Terman和Burks母亲的引文来自信件(L.Terman致R.Tolman,1943)。

伯克利招生悖论的原文出处是Bickel、Hammel和O’Connell(1975),后面Bickel与Kruskal之间的通信可在Fairley和Mosteller(1977)中找到。

VanderWeele(2014是“吸烟基因”例子的来源,Bierrut和Cesarini(2015讲述了该基因是如何被发现的故事。

Welling等人(2012和Kragh等人(2013讲述了在海湾战争之前及期间关于止血带的不可思议的历史。后一篇文章是以个人化和娱乐化的风格撰写而成,这对于学术刊物来说是很不寻常的。Kragh等人(2015描述了本书提到的关于止血带的研究成果,遗憾的是未能证明止血带能提高伤患存活率。

参考文献

Baron, R., and Kenny, D. (1986). The moderator-mediator variable distinction in social psychological research: Conceptual, strategic, and statistical considerations. Journal of Personality and Social Psychology 51: 1173–1182.

Bickel, P. J., Hammel, E. A., and O’Connell, J. W. (1975). Sex bias in graduate admissions: Data from Berkeley. Science 187: 398–404.

Bierut, L., and Cesarini, D. (2015). How genetic and other biological factors interact with smoking decisions. Big Data 3: 198–202.

Burks, B. S. (1926). On the inadequacy of the partial and multiple correlation technique(parts I–II). Journal of Experimental Psychology 17: 532–540, 625–630.

Burks, F., to Mrs. Terman. (June 16, 1943). Correspondence. Lewis M. Terman Archives,Stanford University.

Ceglowski, M. (2010). Scott and scurvy. Idle Words (blog). Available at:http://www.idlewords.com/2010/03/scott_and_scurvy.htm (posted:March 6, 2010).

Cole, S., and Hernán, M. (2002). Fallibility in estimating direct effects.International Journal of Epidemiology 31: 163–165.

De Stavola, B. L., Daniel, R. M., Ploubidis, G. B., and Micali, N.(2015). Mediation analysis with intermediate confounding. American Journal of Epidemiology 181:64–80.

Fairley, W. B., and Mosteller, F. (1977). Statistics and Public Policy. Addison-Wesley,Reading, MA.

Imai, K., Keele, L., and Yamamoto, T. (2010). Identifcation, inference, and sensitivity analysis for causal mediation effects. Statistical Science 25: 51–71.

King, D. B., Montañez Ramírez, L., and Wertheimer, M. (1996). Barbara Stoddard Burks:Pioneer behavioral geneticist and humanitarian. In Portraits of Pioneers in Psychology(C. W. G. A. Kimble and M. Wertheimer,eds.), vol. 2. Erlbaum Associates, Hillsdale,NJ, 212–225.

Kline, R. B. (2015). The mediation myth. Chance 14: 202–213.

Kragh, J. F., Jr., Nam, J. J., Berry, K. A., Mase, V. J., Jr., Aden, J. K.,III, Walters, T. J.,Dubick, M. A., Baer, D. G., Wade, C. E., and Blackbourne, L. H. (2015). Transfusion for shock in U.S. military war casualties with and without tourniquet use. Annals of Emergency Medicine 65: 290–296.

Kragh, J. F., Jr., Walters, T. J., Westmoreland, T., Miller, R. M.,Mabry, R. L., Kotwal, R.S., Ritter, B. A., Hodge, D. C., Greydanus, D. J., Cain, J. S., Parsons, D. S., Edgar,E. P., Harcke, T.,Baer, D. G., Dubick, M. A., Blackbourne, L. H., Montgomery,H. R.,Holcomb, J. B., and Butler, F. K. (2013). Tragedy into drama: An American history of tourniquet use in the current war. Journal of Special Operations Medicine 13: 5–25.

Lewis, H. (1972). Medical aspects of polar exploration: Sixtieth anniversary of Scott’s last expedition. Journal of the Royal Society of Medicine 65: 39–42.

MacKinnon, D. (2008). Introduction to Statistical Mediation Analysis. Lawrence Erlbaum Associates, New York, NY.

McDonald, R. (2001). Structural equations modeling. Journal of Consumer Psychology 10:92–93.

Muthén, B., and Asparouhov, T. (2015). Causal effects in mediation modeling. Structural Equation Modeling 22: 12–23.

Pearl, J. (1998). Graphs, causality, and structural equation models.Sociological Methods and Research 27: 226–284.

Pearl, J. (2001). Direct and indirect effects. In Proceedings of the Seventeenth Conference on Uncertainty in Artifcial Intelligence. Morgan Kaufmann, San Francisco, CA, 411–420.

Pearl, J. (2014). Interpretation and identifcation of causal mediation. Psychological Methods 19: 459–481.

Robins, J., and Greenland, S. (1992). Identifability and exchangeability for direct and indirect effects. Epidemiology 3: 143–155.

Rubin, D. (2004). Direct and indirect causal effects via potential outcomes. Scandinavian Journal of Statistics 31: 161–170.

Rubin, D. (2005). Causal inference using potential outcomes: Design,modeling, decisions.Journal of the American Statistical Association 100: 322–331.

Shpitser, I. (2013). Counterfactual graphical models for longitudinal mediation analysis with unobserved confounding. Cognitive Science 37: 1011–1035.

Terman, L., to Tolman, R. (August 6, 1943). Correspondence. Lewis M. Terman Archives,Stanford University.

VanderWeele, T. (2014). A unifcation of mediation and interaction:A four-way decomposition. Epidemiology 25: 749–761.

VanderWeele, T. (2015). Explanation in Causal Inference: Methods for Mediation and Interaction. Oxford University Press, New York, NY.

Welling, D., MacKay, P., Rasmussen, T., and Rich, N. (2012). A brief history of the tourniquet. Journal of Vascular Surgery 55: 286–290.

第十章 大数据,人工智能和大问题 注释书目

Harris(2012是关于这一长久的自由意志辩论的一篇参考文献。相容派哲学家的代表作有Mumford和Anjum(2014以及Dennett(2003)。

智能体的人工智能概念化可见Russell和Norvig(2003)以及Wooldridge(2009)。关于智能体的哲学观点汇编于Bratman(2007)。Forney等人(2017)描述了一个基于意图的学习系统。

在2017年阿西洛马会议上商定的“普惠人工智能”23项原则可在Future of Life Instirute(2017)找到。

参考文献

Bratman, M. E. (2007). Structures of Agency: Essays. Oxford University Press, New York, NY. Brockman, J. (2015). What to Think About Machines That Think. HarperCollins, New York, NY.

Dennett, D. C. (2003). Freedom Evolves. Viking Books, New York, NY.

Forney, A., Pearl, J., and Bareinboim, E. (2017). Counterfactual datafusion for online reinforcement learners. Proceedings of the 34th International Conference on Machine Learning. Proceedings of Machine Learning Research 70: 1156–1164.

Future of Life Institute. (2017). Asilomar AI principles. Available at: https://futureoflife.org/ai-principles (accessed December 2, 2017).

Harris, S. (2012). Free Will. Free Press, New York, NY.

Mumford, S., and Anjum, R. L. (2014). Causation: A Very Short Introduction (Very Short Introductions). Oxford University Press, New York, NY.

Russell, S. J., and Norvig, P. (2003). Artifcial Intelligence: A Modern Approach. 2nd ed.Prentice Hall, Upper Saddle River, NJ.

Wooldridge, J. (2009). Introduction to Multi-agent Systems. 2nd ed. John Wiley and Sons,New York, NY.

上一章 封面 书架 已读完