Robustness Analysis as Explanatory Reasoning

Schupbach, Jonah N.

doi:10.1093/bjps/axw008

Cited by 86 publications

(65 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In philosophy of science, a standard way of analyzing scientific methodology is by seeing whether the methodology makes sense from a Bayesian perspective. For example, in this way, Sober (2015) analyzes parsimony inference, 12 Dawid et al (2015) analyze no-alternatives arguments in physics, Schupbach (2018) analyzes robustness analysis, and Myrvold (2016) evaluates the epistemic value of unification. Since the preceding analyses take place in a Bayesian framework, they inherit the limitations and assumptions of Bayesianism.…”

Section: Resultsmentioning

confidence: 99%

Justifying the Norms of Inductive Inference

Vassend¹

2022

The British Journal for the Philosophy of Science

View full text Add to dashboard Cite

Abstract Bayesian inference is limited in scope because it cannot be applied in idealized contexts where none of the hypotheses under consideration is true and because it is committed to always using the likelihood as a measure of evidential favouring, even when that is inappropriate. The purpose of this article is to study inductive inference in a very general setting where finding the truth is not necessarily the goal and where the measure of evidential favouring is not necessarily the likelihood. I use an accuracy argument to argue for probabilism and I develop a new kind of argument to argue for two general updating rules, both of which are reasonable in different contexts. One of the updating rules has standard Bayesian updating, Bissiri et al.’s ([2016]) general Bayesian updating, Douven’s ([2016]) IBE-based updating, and my (Vassend ([forthcoming]) quasi-Bayesian updating as special cases. The other updating rule is novel. 1Introduction2Why Crediblity Functions Should Be Probabilistic3Deriving the Updating Rules3.1The combination step3.2The normalization step3.3Characterizations of inferential and predictive updating4Discussion of Inferential and Predictive Updating4.1The difference between inferential updating and predictive updating4.2The relationship between inferential updating and other updating procedures5ConclusionAppendix

show abstract

Section: Resultsmentioning

confidence: 99%

Justifying the Norms of Inductive Inference

Vassend¹

2022

The British Journal for the Philosophy of Science

View full text Add to dashboard Cite

show abstract

“…By eliminating or discriminating against hypothetical alternative explanations of the robust result, robustness analysis may be able to determine that a particular inference process is in fact reliable (cf. Schupbach 2016).…”

Section: Robustness Analysismentioning

confidence: 99%

Extrapolation and the Russo–Williamson thesis

Wilde

Parkkinen

2017

Synthese

View full text Add to dashboard Cite

A particular tradition in medicine claims that a variety of evidence is helpful in determining whether an observed correlation is causal. In line with this tradition, it has been claimed that establishing a causal claim in medicine requires both probabilistic and mechanistic evidence. This claim has been put forward by Federica Russo and Jon Williamson. As a result, it is sometimes called the Russo-Williamson thesis. In support of this thesis, Russo and Williamson appeal to the practice of the International Agency for Research on Cancer (IARC). However, this practice presents some problematic cases for the Russo-Williamson thesis. One response to such cases is to argue in favour of reforming these practices. In this paper, we propose an alternative response according to which such cases are in fact consistent with the Russo-Williamson thesis. This response requires maintaining that there is a role for mechanism-based extrapolation in the practice of the IARC. However, the response works only if this mechanism-based extrapolation is reliable, and some have argued against the reliability of mechanism-based extrapolation. Against this, we provide some reasons for believing that reliable mechanism-based extrapolation is going on in the practice of the IARC. The reasons are provided by appealing to the role of robustness analysis.

show abstract

“…However, the relevance of robustness analysis for explanation has not been systematically explored. A notable exception is a recent contribution by Schupbach (2016). Schupbach proposes that robustness analysis can be interpreted as an explanatory enterprise.…”

Section: Robustness Analysismentioning

confidence: 99%

“…Assume that we want to check whether some idealizations in a model M are responsible for the explanation of a property P or whether the explanation is independent of these idealizations. According to Schupbach (2016), we can do this using robustness analysis. Assume, further, that we construct two models, M 1 and M 2 ; that, in these two models, different idealizations from M are removed; and that we succeed in deriving the property P from M 1 and M 2 .…”

Section: Further Generalizationsmentioning

confidence: 99%

The Volterra Principle Generalized

Räz¹

2017

Philos. of Sci.

View full text Add to dashboard Cite

argue that the Volterra Principle can be derived from multiple predator-prey models and that, therefore, the Volterra Principle is a prime example for robustness analysis. In the current article, I give new results regarding the Volterra Principle, extending Weisberg's and Reisman's work, and I discuss the consequences of these results for robustness analysis. I argue that we do not end up with multiple, independent models but rather with one general model. I identify the kind of situation in which this generalization approach may occur, and I analyze the generalized Volterra Principle from an explanatory perspective.

show abstract

Robustness Analysis as Explanatory Reasoning

Cited by 86 publications

References 32 publications

Justifying the Norms of Inductive Inference

Justifying the Norms of Inductive Inference

Extrapolation and the Russo–Williamson thesis

The Volterra Principle Generalized

Contact Info

Product

Resources

About