2.7 Summary: Chapter 2

The differences between the Bayesian and Frequentist inferential approaches are philosophical, including as pertains to the role of probability; pedagogical, in particular as relates to the use of inference to inform decision making; and methodological, as having differences in their mathematical and computational frameworks. Although at methodological level, the debate has become considerably muted, except for some aspects of inference, with the recognition that each approach has a great deal to contribute to statistical practice ((Good 1992), (M. J. Bayarri and Berger 2004), (R. Kass 2011)). As Bradley Efron said “Computer-age statistical inference at its most successful combines elements of the two philosophies” (Efron and Hastie 2016, p.~ 35-36).

References

Bayarri, M. J., and J. Berger. 2004. “The Interplay of Bayesian and Frequentist Analysis.” Statistical Science 19 (1): 58–80.
Efron, Bradley, and Trevor Hastie. 2016. Computer Age Statistical Inference. Vol. 5. Cambridge University Press.
Good, I. J. 1992. “The Bayes/Non Bayes Compromise: A Brief Review.” Journal of the American Statistical Association 87 (419): 597–606.
Kass, R. 2011. “Statistical Inference: The Big Picture.” Statistical Science 26 (1): 1–9.