/predictiveValue

Primary LanguageTeXGNU General Public License v3.0GPL-3.0

Predictive Value

Drawing on recent work in Bayesian epistemology and predictive modelling, this project explores the conceputal underpinnings of the value of predictions as tool for epistemic justification in biomedical research.

Predictive value assessment is conceptually connected but distinct from risk of bias evaluation, uncertainty modelling, and many other excieting fields of epistemic research in bioethics, epidemiology, statistics and biomedicine in general.

Probability-Raising Account (with Epistemic Probabilities)

Evidence E confirms hypothesis H relative to background K iff:

Prob(H/E & K) > Prob(H/E), where Prob is an epistemic probability function.

References

Goldman, Alvin I, and Matthew McGrath. 2015. Epistemology: A Contemporary Introduction. Oxford University Press.