Corey Dethier

In an influential paper, Wendy Parker argues that agreement across climate models isn’t a reliable marker of confirmation in the context of cutting-edge climate science. In this paper, I argue that while Parker’s conclusion is generally correct, there is an important class of exceptions. Broadly speaking, agreement is not a reliable marker of confirmation when the hypotheses under consideration are mutually consistent—when, e.g., we’re concerned with overlapping ranges. Since many cutting-edge questions in climate modeling require making distinctions between mutually consistent hypotheses, agreement across models will be generally unreliable in this domain. In cases where we are only concerned with mutually exclusive hypotheses, by contrast, agreement across climate models is plausibly a reliable marker of confirmation.

The Intergovernmental Panel on Climate Change (IPCC) often qualifies its statements by use of probabilistic “likelihood” language. In this paper, I show that this language is not properly interpreted in either frequentist or Bayesian terms—simply put, the IPCC uses both kinds of statistics to calculate these likelihoods. I then offer a deflationist interpretation: the probabilistic language expresses nothing more than how compatible the evidence is with the given hypothesis according to some method that generates normalized scores. I end by drawing some tentative normative conclusions.

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.

Climate scientists frequently employ heavily idealized models. How should these models be interpreted? Some philosophers have advanced a possibilist interpretation: climate models stand in for possible scenarios that could occur, but do not provide information about how probable those scenarios are. The present paper argues that possibilism is (a) undermotivated, (b) incompatible with successful practices in the science, and (c) unable to correct for known biases. The upshot is that the models should be interpreted probabilistically in at least some cases.

A number of philosophers of science have argued that there are important differences between robustness in modeling and experimental contexts, and—in particular—many of them have claimed that the former is non-confirmatory. In this paper, I argue for the opposite conclusion: robust hypotheses are confirmed under conditions that do not depend on the differences between and models and experiments—that is, the degree to which the robust hypothesis is confirmed depends on precisely the same factors in both situations. The positive argument turns on the fact that confirmation theory doesn’t recognize a difference between different sources of evidence. Most of the paper is devoted to rebutting various objections designed to show that it should. I end by explaining why philosophers of science have (often) gone wrong on this point.

Over the last twenty-five years, climate scientists working on the attribution of climate change to humans have developed increasingly sophisticated statistical models in a process that can be understood as a kind of calibration: the gradual changes to the statistical models employed in attribution studies served as iterative revisions to a measurement(-like) procedure motivated primarily by the aim of neutralizing particularly troublesome sources of error or uncertainty. This practice is in keeping with recent work on the evaluation of models more generally that views models as tools for particular tasks: what drives the process is the desire for models that provide more reliable grounds for inference rather than accuracy to the underlying mechanisms of data-generation.

I argue that the appropriateness of an assertion is sensitive to context—or, really, the “common ground”—in a way that hasn’t previously been emphasized by philosophers. This kind of context-sensitivity explains why some scientific conclusions seem to be appropriately asserted even though they are not known, believed, or justified on the available evidence. I then consider other recent attempts to account for this phenomenon and argue that if they are to be successful, they need to recognize the kind of context-sensitivity that I argue for.

The best and most popular argument for probabilism is the accuracy-dominance argument, which purports to show that alethic considerations alone support the view that an agent’s degrees of belief should always obey the axioms of probability. I argue that extant versions of the accuracy-dominance argument face a problem. In order for the mathematics of the argument to function as advertised, we must assume that every omniscient credence function is classically consistent; there can be no worlds in the set of dominance-relevant worlds that obey some other logic. This restriction cannot be motivated on alethic grounds unless we’re also willing to accept that rationality requires belief in every metaphysical necessity, as the distinction between a priori logical necessities and a posteriori metaphysical ones is not an alethic distinction. To justify the restriction to classically consistent worlds, non-alethic motivation is required. And thus, if there is a version of the accuracy-dominance argument in support of probabilism, it isn’t one that is grounded in alethic considerations alone.

Philosophy of science has witnessed substantial recent debate over the existence of a structural analogue of chaos, which is alleged to spell trouble for certain uses of climate models. The debate over the analogy can and should be separated from its alleged epistemic implications: chaos-like behavior is neither necessary nor sufficient for small dynamical misrepresentations to generate erroneous results. The kind of sensitivity that matters in epistemology is one that induces unsafe beliefs, and the existence of a structural analogue to chaos is better seen as an explanation for known safety failures than as providing evidence for unknown ones.

Recently, both evolutionary anthropologists and some philosophers have argued that cooperative social settings unique to humans play an important role in the development of both our cognitive capacities and what Michael Tomasello terms the “construction” of “normative rationality” or “a normative point of view as a self-regulating mechanism.” In this article, I use evolutionary game theory to evaluate the plausibility of the claim that cooperation fosters epistemic rationality. Employing an extension of signal-receiver games that I term “telephone games,” I show that cooperative contexts work as advertised: under plausible conditions, these scenarios favor epistemically rational agents over irrational ones designed to do just as well as them in non-interactive contexts. I then show that the basic results are strengthened by introducing complications that make the game more realistic.

Pierre Duhem’s influential argument for holism relies on a view of the role that background theory plays in testing: according to this still common account of “auxiliary hypotheses,” elements of background theory serve as truth-apt premises in arguments for or against a hypothesis. I argue that this view is mistaken. Rather than serving as truth-apt premises in arguments, auxiliary hypotheses are employed as “epistemic tools”: instruments that perform specific tasks in connecting our theoretical questions with the world but that are not premises in arguments. On the resulting picture, the acceptability of an auxiliary hypothesis depends not on its truth but on contextual factors such as the task or purpose it is put to and the other tools employed alongside it.

Wilson [Dialectica 63:525–554, 2009], Moore [Int Stud Philos Sci 26:359–380, 2012], and Massin [Br J Philos Sci 68:805–846, 2017] identify an overdetermination problem arising from the principle of composition in Newtonian physics. I argue that the principle of composition is a red herring: what’s really at issue are contrasting metaphysical views about how to interpret the science. One of these views—that real forces are to be tied to physical interactions like pushes and pulls—is a superior guide to real forces than the alternative, which demands that real forces are tied to “realized” accelerations. Not only is the former view employed in the actual construction of Newtonian models, the latter is both unmotivated and inconsistent with the foundations and testing of the science.

William Whewell’s account of induction differs dramatically from the one familiar from twentieth-century debates. I argue that Whewell’s induction can be usefully understood by comparing the difference between his views and more standard accounts to contemporary debates between semantic and syntactic views of theories: rather than understanding inductive inference as capturing a relationship between sentences or propositions, Whewell understands it as a method for constructing a model of the world. The difference between this view and the more familiar picture of induction is reflected in other aspects of Whewell’s philosophy of science, particularly his treatment of consilience and the order of discovery.