原因、假说选择与最佳解释推理

科学哲学领域的方法论研究者提出了各种对“最佳解释”,“融贯性”或者“统合性”的概率测度.这些测度如果有用,至少在某些情况下依赖它们作解释性推理应该比因果推理中通常用的统计方法更准确.格拉斯(2012)发现,大多数此类测度在小样本的情况下都不优于通常统计方法中用的似然度(likelihood)或后验概率.此后,格拉斯(2013)比较了他定义的测度和后验概率对解决一类假说选择问题的优劣.在该类问题中,需要从一组互不相容且非此即彼的假说中择一,但假说的概率未知.他的结果显示,在似然度已知而主观的先验概率和真实的概率分布不同的情况下,如果样本很小,极大化他的测度选择假说可以比极大化后验概率更准确.本文在格拉斯的框架下探究一些一致的模型选择方法在有限样本下的准确性.笔者发现不同方法在准确性上的优劣依赖于真实假说的分布以及所采用的主观先验概率.虽然很多方法可能在所有设置下都不是最优,但也没有方法在所有设置下都是最优.笔者认为,如果对真实假说的分布和主观先验概率没有限定,讨论哪种方法在样本量不大的情况下能更准确的选出真假说意义不大.     

《现代归纳逻辑的哲学视野》述评

以对归纳概率的多元主义解释研究作为切入点,解析逻辑哲学的核心理念以及如何应用于非经典逻辑,尤其是现代归纳逻辑。与此同时,从特定角度对我国归纳逻辑梯队三代人的成长作了简要的历史性评述。     

Is there a stability problem for Bayesian noncommutative probabilities?

A stability condition for Bayesian statistical inference, which Redei [(1992). When can non-commutative statistical inference be Bayesian? International Studies in the Philosophy of Science, 6, 129–132; (1998). Quantum logic in algebraic approach. Dordrecht: Kluwer Academic Publishers] formulated as a rationality constraint holding in classical probability theory, is shown to fail in quantum mechanics. That allegedly challenges a Bayesian interpretation of quantum probabilities. In this paper we demonstrate that Redei's argument does not apply to quantum mechanics. Moreover, we provide a solution to the problem of Bayesian noncommutative statistical inference arising from the violation of stability condition in general probability spaces.     

From sunspots to the Southern Oscillation: confirming models of large-scale phenomena in meteorology

The epistemic problem of assessing the support that some evidence confers on a hypothesis is considered using an extended example from the history of meteorology. In this case, and presumably in others, the problem is to develop techniques of data analysis that will link the sort of evidence that can be collected to hypotheses of interest. This problem is solved by applying mathematical tools to structure the data and connect them to the competing hypotheses. I conclude that mathematical innovations provide crucial epistemic links between evidence and theories precisely because the evidence and theories are mathematically described.     

老证据问题的成因与解决对策探析

老证据问题起源于美国当代哲学家格莱莫尔针对贝叶斯主义所提出的责难,该问题所展示的困境是,贝叶斯认证理论似乎不能解释此前已知的证据如何给受检假说提供新的支持.本文从分析格莱莫尔论证的前提着手,指出他没有恰当区分已知事实与背景知识以及没有留意贝叶斯检验模型对于多理论竞争框架的承诺是导致老证据问题的关键,并在此基础上探讨贝叶...     

A remark on Fuchs’ Bayesian interpretation of quantum mechanics

Quantum mechanics is a theory whose foundations spark controversy to this day. Although many attempts to explain the underpinnings of the theory have been made, none has been unanimously accepted as satisfactory. Fuchs has recently claimed that the foundational issues can be resolved by interpreting quantum mechanics in the light of quantum information. The view proposed is that quantum mechanics should be interpreted along the lines of the subjective Bayesian approach to probability theory. The quantum state is not the physical state of a microscopic object. It is an epistemic state of an observer; it represents subjective degrees of belief about outcomes of measurements. The interpretation gives an elegant solution to the infamous measurement problem: measurement is nothing but Bayesian belief updating in a analogy to belief updating in a classical setting. In this paper, we analyze an argument that Fuchs gives in support of this latter claim. We suggest that the argument is not convincing since it rests on an ad hoc construction. We close with some remarks on the options left for Fuchs’ quantum Bayesian project.     

The Diversity Principle and the Little Scientist Hypothesis

The remarkable transition from helpless infant to sophisticatedfive-year-old has long captured the attention of scholars interested inthe discovery of knowledge. To explain these achievements, developmentalpsychologists often compare children's discovery procedures to those ofprofessional scientists. For the child to be qualified as a ``littlescientist', however, intellectual development must be shown to derivefrom rational hypothesis selection in the face of evidence. In thepresent paper we focus on one dimension of rational theory-choice,namely, the relation between hypothesis confirmation and evidencediversity. Psychological research suggests cultural variability inappreciating evidence diversity and lack of such appreciation by youngchildren. Before reaching conclusions about the ``little scientist'thesis, however, it is essential to normatively analyze the diversityissue. We undertake such an analysis within a Bayesianperspective.     

迪昂-蒯因问题及其解答

迪昂-蒯因问题是：在什么条件下，一个理论的某一假设可以被证据反驳？迪昂-蒯因论点对此给出否定的回答，即否认有这样的条件。仅仅承认迪昂一蒯因论点的逻辑合理性而否认其实用上的正当性，那就是所谓的“迪昂-蒯因弱论点”；如果同时承认迪昂一蒯因论点的逻辑合理性和实用正当性，那就是“迪昂-蒯因强论点”。波普尔所持的是弱论点而反对强论点，拉卡托斯和库恩虽然也反对强论点但却有条件地接受它。拉卡托斯的条件是：当一个研究纲领处于进步的问题转换；库恩的条件是：当一个范式处于常规科学。这里给出的贝叶斯方案是对拉卡托斯和库恩观点的逻辑重建。     

论豪森对无奇迹论证的反驳与推进

作为实在论辩护的核心策略之一,无奇迹论证试图从科学的经验性成功推论其"近似真理性",并以"无奇迹"作为置信度指标.豪森分析了无奇迹论证的基本逻辑,批评了其在"近似真理"概念上的问题与逻辑困境,并通过揭示论证过程中的基础概率谬误否定了其逻辑有效性.随后,通过引入主观概率解释以及"休谟不等式",豪森提出了一个逻辑上有效的无...