贝叶斯方法与归纳合理性问题——拉姆齐、布鲁诺·德·菲耐蒂和豪森的观点之比较

贝叶斯方法论的创始人拉姆齐和布鲁诺.德.菲耐蒂把归纳合理性问题看作初始概率的合理指派问题,拉姆齐最终将其归结为一种能够自我支持的有用的习惯。相比之下,德.菲耐蒂的归纳合理性理论更为深入,因为他所证明的意见收敛定理为拉姆齐所说的习惯提供了逻辑的辩护。不过,他们二人的归纳辩护都存在一定的缺陷,而且或多或少地表现出向休谟的心理主义立场靠拢的趋向。豪森曾试图为贝叶斯条件化原则进行辩护,但后来却放弃了这一努力而完全倒向休谟的立场。笔者认为,如果把休谟哲学和康德哲学在贝叶斯主义的框架内互补起来,那将为归纳问题的解决开辟更为广阔的前景。     

纯粹逻辑的贝叶斯主义及其哲学效应

"纯粹逻辑的贝叶斯主义",是C.豪森近年来发展出的一个研究纲领。他认为概率演算的布德诺.德.菲耐蒂公理化系统是纯粹逻辑的,而包含可列可加性的公理系统则破坏了逻辑一致性原则。基于"方程可解性"概念所建立的形式类比展示了概率一致性和演绎一致性之间的平行关系。这一纲领对逻辑全能问题、休谟问题以及条件化规则的合理性问题都提出了独到而统合的解决。然而,该纲领仍面临着"杜宾(Dubin)问题"的挑战,同时也回避了一些像简单性和真理的关系这样有意义的哲学问题的探讨。     

无差别原则与贝叶斯疑难

无差别原则(the Principle of Indifference)作为确定基本概率的原则之一,在概率论、统计学和现代归纳逻辑中占居重要的地位。不过,有趣的是,人们对于无差别原则的质疑正如对它的使用一样一直没有间断。无差别原则的致命缺陷在于它会导致逻辑悖论,即无差别悖论。无差别原则的这种矛盾品格使18世纪的数学家、贝叶斯方法的创始人贝叶斯(T.Bayes)处于一种尴尬的境地。一、无差别原则“无差别原则”这个名称得自于现代归纳逻辑的创始人之一凯恩斯(John M.Keynes),但是事实上这个原则几乎是伴随概率概念一道出现的。早在18世纪初概率论处于草…     

全国报刊部分哲学论文索引

全国报刊部分哲学论文索引（１９９４年４月１１日至同年５月１０日）马列主义经典作家思想研究略论马克思和恩格斯在俄国公社问题上的“不同意见”：驳“马恩对立论”／毛石成／学术界（合肥）．１９９４，２．１～７评斯大林的自然主义的辩证唯物主义世界观（２）／丛大...     

基础概率在贝叶斯推理中的作用

针对贝叶斯推理研究中基础概率忽略现象的争论,直接操纵基础概率水平,考察被试在贝叶斯推理时是否加工了基础概率信息。结果表明,低基础概率组后验概率估计显著低,无基础概率组后验概率估计反应时显著短于有基础概率组。被试在各种条件下估计的正确率都较低,说明对基础概率在贝叶斯推理中的作用考虑不充分。     

基于等级反应模型的规则空间方法

本研究基于Tatsuoka的规则空间方法, 对理想反应模式与异常反应指标进行了扩展, 推导了多级评分项目下规则空间方法的算法公式。在4种属性层级结构(发散型、收敛型、线型与无结构型)×4种“失误”作答概率(2%、5%、10%与15%)测验情境下, 以属性模式判准率、被试属性判准率、敏感性与特异性为指标, 检验了多级评分项目下规则空间方法的分类准确性。结果表明：(1) 基于多级评分项目构建的异常反应指标, 能有效地对被试进行分类与解释, 且0-1评分项目下异常反应指标及其性质都是多级评分下的特例; (2) 随着“失误”作答概率的增加, 4种属性层级结构的分类准确性都会降低; (3) 线型和收敛型的分类准确性明显好于发散型与无结构型; (4) 纯规则点的分布对规则空间方法的分类准确性有显著影响。     

有关条件推理中概率效应的实验研究

通过预备实验选取了四种不同条件概率的条件规则和四种不同前后件概率组合的条件规则作为实验材料,以大学生为被试,考察了两种概率因素(条件概率和前后件概率)对条件推理的演绎形式(MP、DA、AC、MT)以及变通形式(四卡问题)的影响。结果表明,两种概率因素对四种条件推理的影响都非常显著,研究进一步证实了人们对四种推理的认可程度主要与范畴前提的概率成正比的结论;但概率因素对四卡问题的解决影响不明显。     

基于YAH（You—Are-Here）地图定向中的方位效应

目的：研究基于YAH地图进行方位判断时是否存在方位效应及其表现形式。方法：90名被试分为三组参加三个被试内设计实验,实验一为基于YAH地图的绝对朝向判断,实验二为基于YAH地图的相对方位判断,实验三为不同绝对朝向条件下（失匹配）的相对方位判断。结果：绝对朝向判断中存在绝对朝向效应及北优势效应,反应时上表现为“0°〈（90°／180°／270°）〈（45°／135°／225°／315°）”;相对方位判断中存在相对方位效应,表现为反应时“（0°／90°／180°／270°）〈（45°／135°／225°／315°）”;失匹配条件下相对方位效应表现为“0°〈（90°／180°／270°）〈（45°／／315°）〈（135°／225°）”,相对方位效应模式不受绝对朝向影响。结论：基于YAH地图定向存在绝对朝向效应及相对方位效应,相对方位效应不受绝对朝向的影响。     

换位棋问题规则的表征与解题正确率间关系的研究

本研究通过对被试求解换位棋过程的记录与分析,重点研究了问题表征在换位棋求解过程中的作用。实验结果表明：（1）正确表征问题规则是解题的必要前提.对问题规则信息的误解和遗漏,是影响解题正确率的重要因素。其中对非隐含问题规则的错误表征也占全部错误表征的很大比率。（2）“关键结构”的发现是解决换位棋的必要条件,对问题规则的错误表征影响“关键结构”的发现.（3）前置问题的解决经验对目标问题的正确表征无显著的影响作用。     

论条件推理中的两种"高概率结论效应"

用随机抽取的139名大学生和研究生被试,对Oaksford设计的4条条件推理规则的认可度,以及对组成这4条条件推理规则的前后件认可度进行了评定,并根据被试对"条件规则"、组成条件规则的"前件"和"后件"等三个因素上的评定结果各区分为"高"和"低"两个水平.而后对被试在不同评定条件下对每条规则的四种推理结果进行了统计分析.实验结果既支持Oaksford等提出的"推理者对组成条件推理规则的不同的前后件概率组合对推理结论的认可度会有影响"这一观点,也支持邱江等得出的"不同的条件概率对推理者进行推理时对结论认可度的高低会有影响"的论断.前者可称之为"前后件概率的高概率结论效应",后者可称之为"条件概率的高概率结论效应".     

Should physicians be Bayesian agents?

Because physicians use scientific inference for the generalizations of individual observations and the application of general knowledge to particular situations, the Bayesian probability solution to the problem of induction has been proposed and frequently utilized. Several problems with the Bayesian approach are introduced and discussed. These include: subjectivity, the favoring of a weak hypothesis, the problem of the false hypothesis, the old evidence/new theory problem and the observation that physicians are not currently Bayesians. To the complaint that the prior probability is subjective, Bayesians reply that there will be ultimate convergence, but the rebuttal to this is that there will not be uniform convergence. Secondly, since the Bayesian scheme favors a weak hypothesis, theories turn out to be a gratuitous risk. The problem with the false hypothesis comes out in the denominator of the theorem, revealing that a factor which is not a theory at all is being considered in the reasoning. On the old evidence/new theory problem old evidence cannot confirm a new theory so that the posterior probability will equal the prior probability. Finally, empiric studies have shown that current physicians are not Bayesians. But on consideration of Bayesian inference as a system of inference, it can be reasoned that physicians should be Bayesians. However, the problem of physicians' and patients' own subjectivity continue to plague this system of medical decision making.     

A geometric principle of indifference

That one's degrees of belief at any one time obey the axioms of probability theory is widely regarded as a necessary condition for static rationality. Many theorists hold that it is also a sufficient condition, but according to critics this yields too subjective an account of static rationality. However, there are currently no good proposals as to how to obtain a tenable stronger probabilistic theory of static rationality. In particular, the idea that one might achieve the desired strengthening by adding some symmetry principle to the probability axioms has appeared hard to maintain. Starting from an idea of Carnap and drawing on relatively recent work in cognitive science, this paper argues that conceptual spaces provide the tools to devise an objective probabilistic account of static rationality. Specifically, we propose a principle that derives prior degrees of belief from the geometrical structure of concepts.     

Bayesian chance

This paper explores how the Bayesian program benefits from allowing for objective chance as well as subjective degree of belief. It applies David Lewis??s Principal Principle and David Christensen??s principle of informed preference to defend Howard Raiffa??s appeal to preferences between reference lotteries and scaling lotteries to represent degrees of belief. It goes on to outline the role of objective lotteries in an application of rationality axioms equivalent to the existence of a utility assignment to represent preferences in Savage??s famous omelet example of a rational choice problem. An example motivating causal decision theory illustrates the need for representing subjunctive dependencies to do justice to intuitive examples where epistemic and causal independence come apart. We argue to extend Lewis??s account of chance as a guide to epistemic probability to include De Finetti??s convergence results. We explore Diachronic Dutch book arguments as illustrating commitments for treating transitions as learning experiences. Finally, we explore implications for Martingale convergence results for motivating commitment to objective chances.     

主观解释的新发展:主体交互解释

主体交互解释是主观解释的发展,它比主观解释具有更为明显的客观性。本文探讨了主体交互概率的测度,主体交互概率形成的条件,主体交互解释与人造客体概率解释一道构造的从主观向完全客观延伸的谱系,以及主体交互解释的恰当性问题。通过探讨这个新近兴起的理论,为人们在确定基本概率时提供了普遍的适用性并使人们避免了主观的随意性。     

Arrow’s theorem and theory choice

In a recent paper (Okasha, Mind 120:83–115, 2011), Samir Okasha uses Arrow’s theorem to raise a challenge for the rationality of theory choice. He argues that, as soon as one accepts the plausibility of the assumptions leading to Arrow’s theorem, one is compelled to conclude that there are no adequate theory choice algorithms. Okasha offers a partial way out of this predicament by diagnosing the source of Arrow’s theorem and using his diagnosis to deploy an approach that circumvents it. In this paper I explain why, although Okasha is right to emphasise that Arrow’s result is the effect of an informational problem, he is not right to locate this problem at the level of the informational input of a theory choice rule. Once the informational problem is correctly located, Arrow’s theorem may be dismissed as a problem.     

A simple proof of a personnel classification theorem

A simple algebraic proof of a theorem defining the optimal solution to the personnel classification problem is given. If a set of constants, one for each job, are known, the theorem indicates that each individual should be classified by adding the constants to the estimates of the individual's productivity in the several jobs and selecting the job for which the resulting sum is highest. The opinions expressed are those of the author and are not to be construed as reflecting official Department of the Army policy.     

Probability and logic

The paper is an attempt to show that the formalism of subjective probability has a logical interpretation of the sort proposed by Frank Ramsey: as a complete set of constraints for consistent distributions of partial belief. Though Ramsey proposed this view, he did not actually establish it in a way that showed an authentically logical character for the probability axioms (he started the current fashion for generating probabilities from suitably constrained preferences over uncertain options). Other people have also sought to provide the probability calculus with a logical character, though also unsuccessfully. The present paper gives a completeness and soundness theorem supporting a logical interpretation: the syntax is the probability axioms, and the semantics is that of fairness (for bets).     

Logic with numbers

Many people regard utility theory as the only rigorous foundation for subjective probability, and even de Finetti thought the betting approach supplemented by Dutch Book arguments only good as an approximation to a utility-theoretic account. I think that there are good reasons to doubt this judgment, and I propose an alternative, in which the probability axioms are consistency constraints on distributions of fair betting quotients. The idea itself is hardly new: it is in de Finetti and also Ramsey. What is new is that it is shown that probabilistic consistency and consequence can be defined in a way formally analogous to the way these notions are defined in deductive (propositional) logic. The result is a free-standing logic which does not pretend to be a theory of rationality and is therefore immune to, among other charges, that of “logical omniscience”.     

The effect of mother-intervener opinion divergence on mothers’ attitudes towards interveners

IntroductionSeveral researchers show that the quality of the relationship between therapist and client is related to a wide range of positive results.AimThe aim of this study was to analyze how the opinions of mothers and interveners about handling problems of adolescents influenced the mothers’ attitudes towards the interveners.MethodsThe methods involved the participation of mothers of adolescents receiving services at the Centre Jeunesse in the Quebec area. Attitudes were measured by a semantic differential and a question. The design included 2 experimental groups divided according to the order of application of the 2 treatments. The condition of convergence or divergence of opinions between a mother and an intervener was forced by an opinion given by the intervener.ResultsThe results demonstrated that the convergence of opinions between mothers and interveners led to more positive attitudes towards the interveners than divergence of opinions.ConclusionThis research was the first to be conducted in an applied setting and treatment was adapted to the most important problem that each mother had with her adolescent. Because the mother's opinions were related to her main problem, the attitudinal response elicited by the interveners’ opinion was strong.     

动机的概率意义——概率归并定理与Monty Hall问题的非贝叶斯解

本文探讨Monty Hall问题认知困惑的形成因素。通过对该问题数学结构的分析,导出一个与该问题的解密切相关的定理——概率归并定理;并依据该定理给出了Monty Hall问题的一种更直观的数学解。