The replication crisis has prompted many to call for statistical reform within the psychological sciences. Here we examine issues within Frequentist statistics that may have led to the replication crisis, and we examine the alternative—Bayesian statistics—that many have suggested as a replacement. The Frequentist approach and the Bayesian approach offer radically different perspectives on evidence and inference with the Frequentist approach prioritising error control and the Bayesian approach offering a formal method for quantifying the relative strength of evidence (...) for hypotheses. We suggest that rather than mere statistical reform, what is needed is a better understanding of the different modes of statistical inference and a better understanding of how statistical inference relates to scientific inference. (shrink)

Although written in Japanese, what the statistical inference is philosophically investigated.

The major competing statistical paradigms share a common remarkable but unremarked thread: in many of their inferential applications, different probability interpretations are combined. How this plays out in different theories of inference depends on the type of question asked. We distinguish four question types: confirmation, evidence, decision, and prediction. We show that Bayesian confirmation theory mixes what are intuitively “subjective” and “objective” interpretations of probability, whereas the likelihood-based account of evidence melds three conceptions of what constitutes an “objective” (...) probability. (shrink)

While the traditional conception of inductive logic is Carnapian, I develop a Peircean alternative and use it to unify formal learning theory, statistics, and a significant part of machine learning: supervised learning. Some crucial standards for evaluating non-deductive inferences have been assumed separately in those areas, but can actually be justified by a unifying principle.

A popular informal argument suggests that statistics about the preponderance of criminal involvement among particular demographic groups partially justify others in making defensive mistakes against members of the group. One could worry that evidence-relative accounts of moral rights vindicate this argument. After constructing the strongest form of this objection, I offer several replies: most demographic statistics face an unmet challenge from reference class problems, even those that meet it fail to ground non-negligible conditional probabilities, even if they did, they introduce (...) new costs likely to cancel out any justificatory contribution of the statistic, but even if they didn’t, demographic facts are the wrong sort to make a moral difference to agents’ negative rights. I conclude that the popular argument should be rejected, and evidence-relative theories do not have the worrisome implication. (shrink)

"Correlation is not causation" is one of the mantras of the sciences—a cautionary warning especially to fields like epidemiology and pharmacology where the seduction of compelling correlations naturally leads to causal hypotheses. The standard view from the epistemology of causation is that to tell whether one correlated variable is causing the other, one needs to intervene on the system—the best sort of intervention being a trial that is both randomized and controlled. In this paper, we argue that some purely correlational (...) data contains information that allows us to draw causal inferences: statistical noise. Methods for extracting causal knowledge from noise provide us with an alternative to randomized controlled trials that allows us to reach causal conclusions from purely correlational data. (shrink)

Causation is a macroscopic phenomenon. The temporal asymmetry displayed by causation must somehow emerge along with other asymmetric macroscopic phenomena like entropy increase and the arrow of radiation. I shall approach this issue by considering ‘causal inference’ techniques that allow causal relations to be inferred from sets of observed correlations. I shall show that these techniques are best explained by a reduction of causation to structures of equations with probabilistically independent exogenous terms. This exogenous probabilistic independence imposes a recursive (...) order on these equations and a consequent distinction between dependent and independent variables that lines up with the temporal asymmetry of causation. (shrink)

Why are conditional degrees of belief in an observation E, given a statistical hypothesis H, aligned with the objective probabilities expressed by H? After showing that standard replies are not satisfactory, I develop a suppositional analysis of conditional degree of belief, transferring Ramsey’s classical proposal to statistical inference. The analysis saves the alignment, explains the role of chance-credence coordination, and rebuts the charge of arbitrary assessment of evidence in Bayesian inference. Finally, I explore the implications of (...) this analysis for Bayesian reasoning with idealized models in science. (shrink)

At its strongest, Hume's problem of induction denies the existence of any well justified assumptionless inductive inference rule. At the weakest, it challenges our ability to articulate and apply good inductive inference rules. This paper examines an analysis that is closer to the latter camp. It reviews one answer to this problem drawn from the VC theorem in statistical learning theory and argues for its inadequacy. In particular, I show that it cannot be computed, in general, whether (...) we are in a situation where the VC theorem can be applied for the purpose we want it to. (shrink)

The paper is dedicated to particular cases of interaction and mutual impact of philosophy and cognitive science. Thus, philosophical preconditions in the middle of the 20th century shaped the newly born cognitive science as mainly based on conceptual and propositional representations and syntactical inference. Further developments towards neural networks and statistical representations did not change the prejudice much: many still believe that network models must be complemented with some extra tools that would account for proper human cognitive traits. (...) I address some real implemented connectionist models that show how ‘new associationism ’ of the neural network approach may not only surpass Humean limitations, but, as well, realistically explain abstraction, inference and prediction. Then I stay on Predictive Processing theories in a little more detail to demonstrate that sophisticated statistical tools applied to a biologically realist ontology may not only provide solutions to scientific problems or integrate different cognitive paradigms but propose some philosophical insights either. To conclude, I touch on a certain parallelism of Predictive Processing and philosophical inferentialism as presented by Robert Brandom. (shrink)

It is well known that there are, at least, two sorts of cases where one should not prefer a direct inference based on a narrower reference class, in particular: cases where the narrower reference class is gerrymandered, and cases where one lacks an evidential basis for forming a precise-valued frequency judgment for the narrower reference class. I here propose (1) that the preceding exceptions exhaust the circumstances where one should not prefer direct inference based on a narrower reference (...) class, and (2) that minimal frequency information for a narrower (non-gerrymandered) reference class is sufficient to yield the defeat of a direct inference for a broader reference class. By the application of a method for inferring relatively informative expected frequencies, I argue that the latter claim does not result in an overly incredulous approach to direct inference. The method introduced here permits one to infer a relatively informative expected frequency for a reference class R', given frequency information for a superset of R' and/or frequency information for a sample drawn from R'. (shrink)

Current debates surrounding the virtues and shortcomings of randomization are symptomatic of a lack of appreciation of the fact that causation can be inferred by two distinct inference methods, each requiring its own, specific experimental design. There is a non-statistical type of inference associated with controlled experiments in basic biomedical research; and a statistical variety associated with randomized controlled trials in clinical research. I argue that the main difference between the two hinges on the satisfaction of (...) the comparability requirement, which is in turn dictated by the nature of the objects of study, namely homogeneous or heterogeneous populations of biological systems. Among other things, this entails that the objection according to which randomized experiments fail to provide better evidence for causation because randomization cannot guarantee comparability is mistaken. (shrink)

During multiple testing, researchers often adjust their alpha level to control the familywise error rate for a statistical inference about a joint union alternative hypothesis (e.g., “H1,1 or H1,2”). However, in some cases, they do not make this inference. Instead, they make separate inferences about each of the individual hypotheses that comprise the joint hypothesis (e.g., H1,1 and H1,2). For example, a researcher might use a Bonferroni correction to adjust their alpha level from the conventional level of (...) 0.050 to 0.025 when testing H1,1 and H1,2, find a significant result for H1,1 (p < 0.025) and not for H1,2 (p > .0.025), and so claim support for H1,1 and not for H1,2. However, these separate individual inferences do not require an alpha adjustment. Only a statistical inference about the union alternative hypothesis “H1,1 or H1,2” requires an alpha adjustment because it is based on “at least one” significant result among the two tests, and so it refers to the familywise error rate. Hence, an inconsistent correction occurs when a researcher corrects their alpha level during multiple testing but does not make an inference about a union alternative hypothesis. In the present article, I discuss this inconsistent correction problem, including its reduction in statistical power for tests of individual hypotheses and its potential causes vis-à-vis error rate confusions and the alpha adjustment ritual. I also provide three illustrations of inconsistent corrections from recent psychology studies. I conclude that inconsistent corrections represent a symptom of statisticism, and I call for a more nuanced inference-based approach to multiple testing corrections. (shrink)

Modern scientific cosmology pushes the boundaries of knowledge and the knowable. This is prompting questions on the nature of scientific knowledge. A central issue is what defines a 'good' model. When addressing global properties of the Universe or its initial state this becomes a particularly pressing issue. How to assess the probability of the Universe as a whole is empirically ambiguous, since we can examine only part of a single realisation of the system under investigation: at some point, data will (...) run out. We review the basics of applying Bayesian statistical explanation to the Universe as a whole. We argue that a conventional Bayesian approach to model inference generally fails in such circumstances, and cannot resolve, e.g., the so-called 'measure problem' in inflationary cosmology. Implicit and non-empirical valuations inevitably enter model assessment in these cases. This undermines the possibility to perform Bayesian model comparison. One must therefore either stay silent, or pursue a more general form of systematic and rational model assessment. We outline a generalised axiological Bayesian model inference framework, based on mathematical lattices. This extends inference based on empirical data (evidence) to additionally consider the properties of model structure (elegance) and model possibility space (beneficence). We propose this as a natural and theoretically well-motivated framework for introducing an explicit, rational approach to theoretical model prejudice and inference beyond data. (shrink)

Despite being a milestone in the history of statistical causal inference, Sewall Wright’s 1918 invention of path analysis did not receive much immediate attention from the statistical and scientific community. Through a careful historical analysis, this paper reveals some previously overlooked philosophical issues concerning the history of causal inference. Placing the invention of path analysis in a broader historical and intellectual context, I portray the scientific community’s initial lack of interest in the method as a natural (...) consequence of relevant scientific and philosophical conditions. In addition to Karl Pearson’s positivist refutation of causation, I contend that the acceptance of path analysis faced several other challenges, including the introduction of a new formalism, conceptual barriers to causal inference, and the lack of model-based statistical thinking. The presence of these challenges shows that the delayed progress in causal inference in the early twentieth century was inevitable. (shrink)

In the last several decades, a confluence of work in the social sciences, philosophy, statistics, and computer science has developed a theory of causal inference using directed graphs. This theory typically rests either explicitly or implicitly on two major assumptions.

The exponential growth of social data both in volume and complexity has increasingly exposed many of the shortcomings of the conventional frequentist approach to statistics. The scientific community has called for careful usage of the approach and its inference. Meanwhile, the alternative method, Bayesian statistics, still faces considerable barriers toward a more widespread application. The bayesvl R package is an open program, designed for implementing Bayesian modeling and analysis using the Stan language’s no-U-turn (NUTS) sampler. The package combines the (...) ability to construct Bayesian network models using directed acyclic graphs (DAGs), the Markov chain Monte Carlo (MCMC) simulation technique, and the graphic capability of the ggplot2 package. As a result, it can improve the user experience and intuitive understanding when constructing and analyzing Bayesian network models. A case example is offered to illustrate the usefulness of the package for Big Data analytics and cognitive computing. (shrink)

This work addresses the autonomous organization of biological systems. It does so by considering the boundaries of biological systems, from individual cells to Home sapiens, in terms of the presence of Markov blankets under the active inference scheme—a corollary of the free energy principle. A Markov blanket defines the boundaries of a system in a statistical sense. Here we consider how a collective of Markov blankets can self-assemble into a global system that itself has a Markov blanket; thereby (...) providing an illustration of how autonomous systems can be understood as having layers of nested and self-sustaining boundaries. This allows us to show that: (i) any living system is a Markov blanketed system and (ii) the boundaries of such systems need not be co-extensive with the biophysical boundaries of a living organism. In other words, autonomous systems are hierarchically composed of Markov blankets of Markov blankets—all the way down to individual cells, all the way up to you and me, and all the way out to include elements of the local environment. (shrink)

The article begins by describing two longstanding problems associated with direct inference. One problem concerns the role of uninformative frequency statements in inferring probabilities by direct inference. A second problem concerns the role of frequency statements with gerrymandered reference classes. I show that past approaches to the problem associated with uninformative frequency statements yield the wrong conclusions in some cases. I propose a modification of Kyburg’s approach to the problem that yields the right conclusions. Past theories of direct (...) inference have postponed treatment of the problem associated with gerrymandered reference classes by appealing to an unexplicated notion of projectability . I address the lacuna in past theories by introducing criteria for being a relevant statistic . The prescription that only relevant statistics play a role in direct inference corresponds to the sort of projectability constraints envisioned by past theories. (shrink)

The purpose of this paper is twofold: -/- 1) to highlight the widely ignored but fundamental problem of ‘superpopulations’ for the use of inferential statistics in development studies. We do not to dwell on this problem however as it has been sufficiently discussed in older papers by statisticians that social scientists have nevertheless long chosen to ignore; the interested reader can turn to those for greater detail. -/- 2) to show that descriptive statistics both avoid the problem of superpopulations and (...) can be a powerful tool when used correctly. A few examples are provided. -/- The paper ends with considerations of some reasons we think are behind the adherence to methods that are known to be inapplicable to many of the types of questions asked in development studies yet still widely practiced. (shrink)

In this article, I explore the compatibility of inference to the best explanation (IBE) with several influential models and accounts of scientific explanation. First, I explore the different conceptions of IBE and limit my discussion to two: the heuristic conception and the objective Bayesian conception. Next, I discuss five models of scientific explanation with regard to each model’s compatibility with IBE. I argue that Kitcher’s unificationist account supports IBE; Railton’s deductive–nomological–probabilistic model, Salmon’s statistical-relevance model, and van Fraassen’s erotetic (...) account are incompatible with IBE; and Salmon’s causal–mechanical model is merely consistent with IBE. In short, many influential models of scientific explanation do not support IBE. I end by outlining three possible conclusions to draw: (1) either philosophers of science or defenders of IBE have seriously misconstrued the concept of explanation, (2) philosophers of science and defenders of IBE do not use the term ‘explanation’ univocally, and (3) the ampliative conception of IBE, which is compatible with any model of scientific explanation, deserves a closer look. (shrink)

The 2021 Nobel Prize in Economics recognizes a type of causal model known as the Rubin causal model, or potential outcome framework, which deserves far more attention from philosophers than it currently receives. To spark philosophers' interest, I develop a dialectic connecting the Rubin causal model to the Lewis-Stalnaker debate on a logical principle of counterfactuals: Conditional Excluded Middle (CEM). I begin by playing good cop for CEM, developing a new argument in its favor---a Quine-Putnam-style indispensability argument. This argument is (...) based on the observation that CEM seems to be indispensable to the Rubin causal model, which underpins our best scientific theory of causal inference in health and social sciences---a Nobel Prize-winning theory. Indeed, CEM has long remained a core assumption of the Rubin causal model, despite challenges from within the statistics and economics communities over twenty years ago. I then switch sides to play bad cop for CEM, undermining the indispensability argument by developing a new theory of causal inference that dispenses with CEM while preserving the successes of the original theory (thanks to a new theorem proved here). The key, somewhat surprisingly, is to integrate two approaches to causal modeling: the Rubin causal model, more familiar in health and social sciences, and the causal Bayes net, more familiar in philosophy. The good cop/bad cop dialectic is concluded with a connection to broader philosophical issues, including intertheory relations, the revisability of logic, and the role of background assumptions in justifying scientific inference. (shrink)

This page provides a quick glance at official publications that use either the bayesvl package in R or the BMF analytics (or both). The data will tell a bit about the research community’s efforts made over time and the growth of the bayesvl/BMF analytics community.

Research in experimental philosophy has increasingly been turning to corpus methods to produce evidence for empirical claims, as they open up new possibilities for testing linguistic claims or studying concepts across time and cultures. The present article reviews the quasi-experimental studies that have been done using textual data from corpora in philosophy, with an eye for the modeling and experimental design that enable statistical inference. I find that most studies forego comparisons that could control for confounds, and that (...) only a little less than half employ statistical testing methods to control for chance results. Furthermore, at least some researchers make modeling decisions that either do not take into account the nature of corpora and of the word-concept relationship, or undermine the experiment's capacity to answer research questions. I suggest that corpus methods could both provide more powerful evidence and gain more mainstream acceptance by improving their modeling practices. (shrink)

An important problem with machine learning is that when label number n>2, it is very difficult to construct and optimize a group of learning functions, and we wish that optimized learning functions are still useful when prior distribution P(x) (where x is an instance) is changed. To resolve this problem, the semantic information G theory, Logical Bayesian Inference (LBI), and a group of Channel Matching (CM) algorithms together form a systematic solution. MultilabelMultilabel A semantic channel in the G theory (...) consists of a group of truth functions or membership functions. In comparison with likelihood functions, Bayesian posteriors, and Logistic functions used by popular methods, membership functions can be more conveniently used as learning functions without the above problem. In Logical Bayesian Inference (LBI), every label’s learning is independent. For Multilabel learning, we can directly obtain a group of optimized membership functions from a big enough sample with labels, without preparing different samples for different labels. A group of Channel Matching (CM) algorithms are developed for machine learning. For the Maximum Mutual Information (MMI) classification of three classes with Gaussian distributions on a two-dimensional feature space, 2-3 iterations can make mutual information between three classes and three labels surpass 99% of the MMI for most initial partitions. For mixture models, the Expectation-Maxmization (EM) algorithm is improved and becomes the CM-EM algorithm, which can outperform the EM algorithm when mixture ratios are imbalanced, or local convergence exists. The CM iteration algorithm needs to combine neural networks for MMI classifications on high-dimensional feature spaces. LBI needs further studies for the unification of statistics and logic. (shrink)

The article focuses on prosecutor's fallacy and interrogator's fallacy, the two kinds of reasoning in inferring a suspect's guilt. The prosecutor's fallacy is a combination of two conditional probabilities that lead to unfortunate commission of error in the process due to the inclination of the prosecutor in the establishment of strong evidence that will indict the defendant. It provides a comprehensive discussion of Gerd Gigerenzer's discourse on a criminal case in Germany explaining the perils of prosecutor's fallacy in his application (...) of probability to practical problems. It also discusses the interrogator's fallacy which was introduced by Robert A. J. Matthews as the error on the assumption that confessional evidence can never reduce the probability of guilt. (shrink)

Rationalism, my target, says that in order to have perceptual knowledge, such as that your hand is making a fist, you must “antecedently” (or “independently”) know that skeptical scenarios don’t obtain, such as the skeptical scenario that you are in the Matrix. I motivate the specific form of Rationalism shared by, among others, White (Philos Stud 131:525–557, 2006) and Wright (Proc Aristot Soc Suppl Vol 78:167–212, 2004), which credits us with warrant to believe (or “accept”, in Wright’s terms) that our (...) senses are reliably veridical, where that warrant is one we enjoy by default, that is, without relying on any evidence or engaging in any positive argument. The problem with this form of Rationalism is that, even if you have default knowledge that your senses are reliable, this is not adequate to rule out every kind of skeptical scenario. The problem is created by one-off skeptical scenarios, scenarios that involve a highly reliable perceiver who, by a pure fluke, has a one-off, non-veridical experience. I claim you cannot infer that your present perceptual experience is veridical just on the basis of knowledge of your general reliability. More generally, if you infer that the present F is G, just on the basis of your knowledge that most Fs are Gs, this is what I call statistical inference, and, as I argue, statistical inference by itself does not generate knowledge. I defend this view of statistical inference against objections, including the objection that radical skepticism about our ordinary inductive knowledge will follow unless statistical inference generates knowledge. (shrink)

Decoupling is a general principle that allows us to separate simple components in a complex system. In statistics, decoupling is often expressed as independence, no association, or zero covariance relations. These relations are sharp statistical hypotheses, that can be tested using the FBST - Full Bayesian Significance Test. Decoupling relations can also be introduced by some techniques of Design of Statistical Experiments, DSEs, like randomization. This article discusses the concepts of decoupling, randomization and sparsely connected statistical models (...) in the epistemological framework of cognitive constructivism. (shrink)

Academic institutions migrated to modular teaching-learning amid the COVID-19 pandemic. To ensure the quality of the pedagogical innovations employed, the study determined the students’ evaluation of the faculty prepared instructional modules for the courses they enrolled in during the first and second semesters of Academic Year 2020-2021. Employing a descriptive-correlational research design, the study was participated by 644 students from three colleges who were then available during the data gathering. Data gathered through online surveys were then analyzed using descriptive statistics (...) and Spearman's rank correlation coefficient utilizing jamovi software. Results revealed that the faculty-prepared instructional modules were acceptable and satisfactory to the students. Besides, the students' evaluation of the instructional modules was positively related to their level of satisfaction. Still, the students recommended that a review of the modules be done before sending the modules; a more extended time allotment is considered, and sufficient concrete examples are given in the modules. With this, the faculty concerned are encouraged to review the phases involved in the design, development, and distribution of the instructional modules to make them highly acceptable and very satisfactory to the students while maintaining the quality of both the content and aesthetics of the learning materials. Considering the study’s limitations, further endeavors may be carried out to validate this pedagogical innovation. (shrink)

Five years ago, on May 24, 2019, the computer program ‘bayesvl’ was officially published on R under the name “bayesvl: Visually Learning the Graphical Structure of Bayesian Networks and Performing MCMC with ‘Stan’”. This program (or package) was developed by two founders of the SM3D Portal, Vuong Quan Hoang and La Viet Phuong, to improve the productivity of conducting social research. The package was designed with a pedagogical orientation, supporting users in familiarizing themselves with Bayesian statistical methods, MCMC simulation, (...) and visualization of technical diagnoses and results. (shrink)

To estimate causal relationships, time series econometricians must be aware of spurious correlation, a problem first mentioned by Yule (1926). To deal with this problem, one can work either with differenced series or multivariate models: VAR (VEC or VECM) models. These models usually include at least one cointegration relation. Although the Bayesian literature on VAR/VEC is quite advanced, Bauwens et al. (1999) highlighted that “the topic of selecting the cointegrating rank has not yet given very useful and convincing results”. The (...) present article applies the Full Bayesian Significance Test (FBST), especially designed to deal with sharp hypotheses, to cointegration rank selection tests in VECM time series models. It shows the FBST implementation using both simulated and available (in the literature) data sets. As illustration, standard non informative priors are used. (shrink)

In times of populist mistrust towards experts, it is important and the aim of the paper to ascertain the rationality of arguments from expert opinion and to reconstruct their rational foundations as well as to determine their limits. The foundational approach chosen is probabilistic. However, there are at least three correct probabilistic reconstructions of such argumentations: statistical inferences, Bayesian updating, and interpretive arguments. To solve this competition problem, the paper proposes a recourse to the arguments' justification strengths achievable in (...) the respective situation. (shrink)

Randomization procedures are used in legal and statistical applications, aiming to shield important decisions from spurious influences. This article gives an intuitive introduction to randomization and examines some intended consequences of its use related to truthful statistical inference and fair legal judgment. This article also presents an open-code Java implementation for a cryptographically secure, statistically reliable, transparent, traceable, and fully auditable randomization tool.

Karl Pearson is the leading figure of XX century statistics. He and his co-workers crafted the core of the theory, methods and language of frequentist or classical statistics – the prevalent inductive logic of contemporary science. However, before working in statistics, K. Pearson had other interests in life, namely, in this order, philosophy, physics, and biological heredity. Key concepts of his philosophical and epistemological system of anti-Spinozism (a form of transcendental idealism) are carried over to his subsequent works on the (...) logic of scientific discovery. This article’s main goal is to analyze K. Pearson early philosophical and theological ideas and to investigate how the same ideas came to influence contemporary science, either directly or indirectly – by the use of variant theories, methods and dialects of statistics, corresponding to variant statistical inference procedures and their specific belief calculi. (shrink)

A Boltzmann Brain, haphazardly formed through the unlikely but still possible random assembly of physical particles, is a conscious brain having experiences just like an ordinary person. The skeptical possibility of being a Boltzmann Brain is an especially gripping one: scientific evidence suggests our actual universe’s full history may ultimately contain countless short-lived Boltzmann Brains with experiences just like yours or mine. I propose a solution to the skeptical challenge posed by these countless actual Boltzmann Brains. My key idea is (...) roughly this: the skeptical argument that you’re one of the Boltzmann Brains requires you to make a statistical inference, but the Principle of Total Evidence blocks us from making the inference. I discuss how my solution contrasts with a recent suggestion, made by Sean Carroll and David Chalmers, for how to address the skeptical challenge posed by Boltzmann Brains. And I discuss how my solution handles certain relevant concerns about what to do when we have higher-order evidence indicating that our first-order evidence is misleading. (shrink)

Logical and philosophical literature provides different classifications of reasoning. In the Polish literature on the subject, for instance, there are three popular ones accepted by representatives of the Lvov-Warsaw School: Jan Łukasiewicz, Tadeusz Czeżowski and Kazimierz Ajdukiewicz (Ajdukiewicz in Logika pragmatyczna [Pragmatic Logic]. PWN, Warsaw (1965, 2nd ed. 1974). Translated as: Pragmatic Logic. Reidel & PWN, Dordrecht, 1975). The author of this paper, having modified those classifications, distinguished the following types of reasoning: (1) deductive and (2) non-deductive, and additionally two (...) types of them in each of the two, depending on the manner of combining their premises with the conclusion through the relation of classical logical entailment. Consequently, the four types of reasoning: unilateral deductive (incl. its sub-types: deductive inference and proof), bilateral deductive (incl. complete induction), and reductive (incl. the sub-types: explanation and verification), logically nonvaluable (incl. inference by analogy, statistic inference), correspond to four operators of derivability. They are defined formally on the ground of Tarski’s axiomatic theory of deductive systems, by means of the consequence operation _Cn_ (Tarski in Monatshefte Math Phys 37:361–404, 1930a, C R Soc Sci Lett Vars 23:22–29, 1930b). Also, certain metalogical properties of these operators are given, as well as their relations with Tarski’s consequence operations \(Cn^+\) ( \(Cn^+ = Cn\) ) and dual consequences \(Cn^{-1}\) (Słupecki in Zeszyty Naukowe Uniwersytetu Wrocławskiego Seria B Nr 3:33–40, 1959, Słupecki et al. in Stud Log 29:76–123, 1971, Wybraniec-Skardowska, in: Wybraniec-Skardowska, Bryll (eds) Z badań nad teorią zdań odrzuconych [Studies in the Theory of Rejected Propositions], Series B, Studia i Monografie, Zeszyty Naukowe Wyższej Szkoły Pedagogicznej w Opolu, Opole, 1969), and \(Cn^-\) (Wójcicki in Bull Sect Log 2(2):54–57, 1973)). (shrink)

Climate scientists often apply statistical tools to a set of different estimates generated by an “ensemble” of models. In this paper, I argue that the resulting inferences are justified in the same way as any other statistical inference: what must be demonstrated is that the statistical model that licenses the inferences accurately represents the probabilistic relationship between data and target. This view of statistical practice is appropriately termed “model-based,” and I examine the use of statistics (...) in climate fingerprinting to show how the difficulties that climate scientists encounter in applying statistics to ensemble-generated data are the practical difficulties of normal statistical practice. The upshot is that whether the application of statistics to ensemble-generated data yields trustworthy results should be expected to vary from case to case. (shrink)

I defend the thesis that legal standards of proof are reducible to thresholds of probability. Many reject this thesis because it appears to permit finding defendants liable solely on the basis of statistical evidence. To the contrary, I argue – by combining Thomson's (1986) causal analysis of legal evidence with formal methods of causal inference – that legal standards of proof can be reduced to probabilities, but that deriving these probabilities involves more than just statistics.

Evaluative studies of inductive inferences have been pursued extensively with mathematical rigor in many disciplines, such as statistics, econometrics, computer science, and formal epistemology. Attempts have been made in those disciplines to justify many different kinds of inductive inferences, to varying extents. But somehow those disciplines have said almost nothing to justify a most familiar kind of induction, an example of which is this: “We’ve seen this many ravens and they all are black, so all ravens are black.” This is (...) enumerative induction in itsfullstrength. For it does not settle with a weaker conclusion (such as “the ravens observed in the future will all be black”); nor does it proceed with any additional premise (such as the statistical IID assumption). The goal of this paper is to take some initial steps toward a justification for the full version of enumerative induction, against counterinduction, and against the skeptical policy. The idea is to explore various epistemic ideals, mathematically defined as different modes of convergence to the truth, and look for one that is weak enough to be achievable and strong enough to justify a norm that governs both the long run and the short run. So the proposal is learning-theoretic in essence, but a Bayesian version is developed as well. (shrink)

Unification of natural science and social science is a centuries-old, unmitigated debate. Natural science has a chronological advantage over social science because the latter took time to include many social phenomena in its fold. History of science witnessed quite a number of efforts by social scientists to fit this discipline in a rational if not mathematical framework. On the other hand a tendency among some physicists has been observed especially since the last century to recast a number of social phenomena (...) in the mould of events taking place in physical world and governed by well-known systems and equations of physics. It necessitated the introduction of social physics as a new inter-disciplinary subject. Obviously this attempt is aimed at explaining hitherto unsolved or highly debated issues of social science. Physicists are showing special interest on problems on economics, ranging from some topics of normative economics to the movement of prices of derivatives. Statistics has been widely used in these attempts and at least two sub-disciplines of the subject, namely, stochastic process and time series analysis deserve special mention. All these research activities gave birth to another inter-disciplinary subject named as econophysics. Interestingly, global financial crisis of 2007–08 has revived the need of determination of prices of derivatives in a more accurate manner. This article adumbrates a sketch of the theoretical synthesis between physics and economics and the role played by statistics in this process. (shrink)

The Full Bayesian Significance Test, FBST, is extensively reviewed. Its test statistic, a genuine Bayesian measure of evidence, is discussed in detail. Its behavior in some problems of statistical inference like testing for independence in contingency tables is discussed.

In attempting to form rational personal probabilities by direct inference, it is usually assumed that one should prefer frequency information concerning more specific reference classes. While the preceding assumption is intuitively plausible, little energy has been expended in explaining why it should be accepted. In the present article, I address this omission by showing that, among the principled policies that may be used in setting one’s personal probabilities, the policy of making direct inferences with a preference for frequency information (...) for more specific reference classes yields personal probabilities whose accuracy is optimal, according to all proper scoring rules, in situations where all of the relevant frequency information is point-valued. Assuming that frequency information for narrower reference classes is preferred, when the relevant frequency statements are point-valued, a dilemma arises when choosing whether to make a direct inference based upon relatively precise-valued frequency information for a broad reference class, R, or upon relatively imprecise-valued frequency information for a more specific reference class, R*. I address such cases, by showing that it is often possible to make a precise-valued frequency judgment regarding R* based on precise-valued frequency information for R, using standard principles of direct inference. Having made such a frequency judgment, the dilemma of choosing between and is removed, and one may proceed by using the precise-valued frequency estimate for the more specific reference class as a premise for direct inference. (shrink)

The main goal of this article is to use the epistemological framework of a specific version of Cognitive Constructivism to address Piaget’s central problem of knowledge construction, namely, the re-equilibration of cognitive structures. The distinctive objective character of this constructivist framework is supported by formal inference methods of Bayesian statistics, and is based on Heinz von Foerster’s fundamental metaphor of objects as tokens for eigen-solutions. This epistemological perspective is illustrated using some episodes in the history of chemistry concerning the (...) definition or identification of chemical elements. Some of von Foerster’s epistemological imperatives provide general guidelines of development and argumentation. (shrink)

In recent years, neuroscience has begun to transform itself into a “big data” enterprise with the importation of computational and statistical techniques from machine learning and informatics. In addition to their translational applications such as brain-computer interfaces and early diagnosis of neuropathology, these tools promise to advance new solutions to longstanding theoretical quandaries. Here I critically assess whether these promises will pay off, focusing on the application of multivariate pattern analysis (MVPA) to the problem of reverse inference. I (...) argue that MVPA does not inherently provide a new answer to classical worries about reverse inference, and that the method faces pervasive interpretive problems of its own. Further, the epistemic setting of MVPA and other decoding methods contributes to a potentially worrisome shift towards prediction and away from explanation in fundamental neuroscience. (shrink)

Law-enforcement agencies are increasingly able to leverage crime statistics to make risk predictions for particular individuals, employing a form of inference that some condemn as violating the right to be “treated as an individual.” I suggest that the right encodes agents’ entitlement to a fair distribution of the burdens and benefits of the rule of law. Rather than precluding statistical prediction, it requires that citizens be able to anticipate which variables will be used as predictors and act intentionally (...) to avoid them. Furthermore, it condemns reliance on various indexes of distributive injustice, or unchosen properties, as evidence of law-breaking. (shrink)

The applicability of Bayesian conditionalization in setting one’s posterior probability for a proposition, α, is limited to cases where the value of a corresponding prior probability, PPRI(α|∧E), is available, where ∧E represents one’s complete body of evidence. In order to extend probability updating to cases where the prior probabilities needed for Bayesian conditionalization are unavailable, I introduce an inference schema, defeasible conditionalization, which allows one to update one’s personal probability in a proposition by conditioning on a proposition that represents (...) a proper subset of one’s complete body of evidence. While defeasible conditionalization has wider applicability than standard Bayesian conditionalization (since it may be used when the value of a relevant prior probability, PPRI(α|∧E), is unavailable), there are circumstances under which some instances of defeasible conditionalization are unreasonable. To address this difficulty, I outline the conditions under which instances of defeasible conditionalization are defeated. To conclude the article, I suggest that the prescriptions of direct inference and statistical induction can be encoded within the proposed system of probability updating, by the selection of intuitively reasonable prior probabilities. (shrink)

In this chapter we will deal with “mechanizing” induction, i.e. with ways in which theoretical computer science approaches inductive generalization. In the field of Machine Learning, algorithms for induction are developed. Depending on the form of the available data, the nature of these algorithms may be very different. Some of them combine geometric and statistical ideas, while others use classical reasoning based on logical formalism. However, we are not so much interested in the algorithms themselves, but more on the (...) philosophical and theoretical foundations they share. Thus in the first of two parts, we will examine different approaches and inductive assumptions in two particular learning settings. While many machine learning algorithms work well on a lot of tasks, the interpretation of the learned hypothesis is often difficult. Thus, while e.g. an algorithm surprisingly is able to determine the gender of the author of a given text with about 80 percent accuracy [Argamon and Shimoni, 2003], for a human it takes some extra effort to understand on the basis of which criteria the algorithm is able to do so. With that respect the advantage of approaches using logic are obvious: If the output hypothesis is a formula of predicate logic, it is easy to interpret. However, if decision trees or algorithms from the area of inductive logic programming are based purely on classical logic, they suffer from the fact that most universal statements do not hold for exceptional cases, and classical logic does not offer any convenient way of representing statements which are meant to hold in the “normal case”. Thus, in the second part we will focus on approaches for Nonmonotonic Reasoning that try to handle this problem. Both Machine Learning and Nonmonotonic Reasoning have been anticipated partially by work in philosophy of science and philosophical logic. At the same time, recent developments in theoretical computer science are expected to trig- ger further progress in philosophical theories of inference, confirmation, theory revision, learning, and the semantic and pragmatics of conditionals. We hope this survey will contribute to this kind of progress by building bridges between computational, logical, and philosophical accounts of induction. (shrink)

There are two competing views regarding the role of mechanistic knowledge in inferences about the effectiveness of interventions. One view holds that inferences about the effectiveness of interventions should be based only on data from population-level studies (often statistical evidence from randomised trials). The other view holds that such inferences must be based in part on mechanistic evidence. The competing views are local principles of inference, the plausibility of which can be assessed by a more general normative principle (...) of inference. Bayesianism tells us to base inferences on both the ‘likelihood’ and the ‘prior’. The likelihood represents statistical evidence. One influence on the prior probability of a hypothesis like ‘d causes x’ is mechanistic knowledge of how d causes x. Thus, reasoning about such inferences by appealing to both statistical and mechanistic evidence is vindicated by our best general theory of inference. The primary contribution of this paper is to assess the merits and weaknesses of the arguments on both sides of the debate, using the Bayesian framework. This analysis lends support to those who argue that we should base our causal inferences about interventions in part on mechanistic evidence. (shrink)

The debate between scientific realism and anti-realism remains at a stalemate, making reconciliation seem hopeless. Yet, important work remains: exploring a common ground, even if only to uncover deeper points of disagreement and, ideally, to benefit both sides of the debate. I propose such a common ground. Specifically, many anti-realists, such as instrumentalists, have yet to seriously engage with Sober's call to justify their preferred version of Ockham's razor through a positive account. Meanwhile, realists face a similar challenge: providing a (...) non-circular explanation of how their version of Ockham's razor connects to truth. The common ground I propose addresses these challenges for both sides; the key is to leverage the idea that everyone values some truths and to draw on insights from scientific fields that study scientific inference—namely, statistics and machine learning. This common ground also isolates a distinctively epistemic root of the irreconcilability in the realism debate. (shrink)

Decision-making by a Data and Safety Monitoring Board (DSMB) regarding clinical trial conduct and termination is intricate and largely limited by cases and rules. Decision-making by legal jury is also intricate and largely constrained by cases and rules. In this paper, I argue by analogy that legal decision-making, which strives for a balance between competing demands of conservatism and innovation, supplies a good basis to the logic behind DSMB decision-making. Using the doctrine of precedents in legal reasoning as my central (...) analog will lead us to a decision-theoretic analogy for much more systematic documentation of decisions in clinical trials. My conclusion is twofold: every DSMB decision should articulate a clear general principle (a ratio decidendi) that gives reason for the decision; and all such decisions should be made public. I use Bartha’s (2010) theory of analogical arguments to both frame and assess my argument by analogy. (shrink)