A Comparison of Bayes–Laplace, Jeffreys, and Other Priors

66 citations recorded by the source corpus.

How researchers see this paper

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

Variational Inference for Crowdsourcing (2012, background): “One reasonable choice is Beta(α, 1) prior with α > 1 [17].”
Entropy Inference and the James-Stein Estimator, with Application to Nonlinear Gene Association Networks (2008, methodology): “…plugin entropy estimators, While the multinomial model with Dirichlet prior is standard Bayesian folklore (Gelman et al., 2004), there is no general agreement regarding which assignment of a k is best as noninformative prior—see for instance the discussion in Tuyl et al. (2008) and Geisser (1984).”
Neutral noninformative and informative conjugate beta and gamma prior distributions (2011, background): “Priors with either shape parameter less than 1, especially those close to zero, have been criticized by Tuyl, Gerlach and Mengersen [20], showing by example how posterior distributions seem to be affected too much by the information in the prior.”