Ockham's Razor and Bayesian Analysis

By James O. Berger, W. Jefferys. 1992

Subfields: Statistics and Probability, Probabilistic & Bayesian Methods

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Statistics and Probability

In Probabilistic & Bayesian Methods

Citations in the corpus

Intuitive Theories of Mind: A Rational Approach to False Belief (2005, unknown): “How can we understand the delayed confirmation of the PT model? First, in the initial epoch, the CT model is preferred due to the Bayesian Occam’s razor effect (Jefferys and Berger, 1992): the PT model has additional complexity (the free parameter γ), which is penalized via the posterior probability”
Phylogeography takes a relaxed random walk in continuous space and time. (2010, background): “The negative value accords well with Occam’s Razor, positing support for the simplestmodel in the absence of evidence to the contrary emerging from the data (Berger and Jefferys 1992).”
Maximum likelihood Bayesian averaging of spatial variability models in unsaturated fractured tuff (2003, methodology): “A practical way to eliminate the first difficulty is to adopt the idea of Occam’s window [Jefferys and Berger, 1992; Madigan and Raftery, 1994] according to which one considers only a relatively small set of the most parsimonious models among those which, a priori, appear to be hydrologically most p”
The Multidimensional Nature of Psychopathy: Five Recommendations for Research (2018, background): “Similarly, the time-honored heuristic of Occam’s razor reminds us that when confronted with two hypotheses that fit the data equally well,we should generally select the simpler one (Jefferys and Berger 1992).”
Probabilistic machine learning and artificial intelligence (2015, methodology): “…applying the sum and product rule to get the prediction: Finally, different models can be compared by applying Bayes rule at the level of m : The term P ( D | m ) is the marginal likelihood or model evidence, and implements a preference for simpler models known as Bayesian Ockham’s razor 78,96,97 .”
Adaptive computation and machine learning (1998, background): “As pointed out by several authors, Ockham’s razor is automatically embodied in the Bayesian framework [285, 373] in at least two different ways.”
Unsupervised Learning (2018, unknown): “The decrease in the marginal likelihood as additional parameters are added has been called the automatic Occam’s Razor [59, 60, 61].”
Inference to the Best Explanation (IBE) Versus Explaining for the Best Inference (EBI) (2015, background): “One could argue individually for the rationality of favoring each virtue, as seen—for instance—in Bayesian arguments for favoring simpler hypotheses (e.g., Jefferys and Berger 1992).”
Action understanding as inverse planning. (2009, methodology): “Our framework explains inferences about whether an agent is pursuing a simple goal or a complex goal with subgoals through a version of the Bayesian Occam’s razor (Jefferys & Berger, 1992).”
Assessment of pile drivability using random forest regression and multivariate adaptive regression splines (2019, background): “From the perspective of Bayesian estimation, the regularisation term corresponds to the prior probability of the model (Jefferys and Berger 1992).”
Action and Perception as Divergence Minimization (2020, background): “…models or by modeling the behavior of natural agents as divergence minimization. overconﬁdence (Jaynes, 1957), Occam’s razor to prevent overﬁtting (Jefferys and Berger, 1992), bounded rationality to halt optimization before reaching the point solution (Ortega and Braun, 2011), and…”