Michael Betancourt

The Prior Can Often Only Be Understood in the Context of the Likelihood

A key sticking point of Bayesian analysis is the choice of prior distribution, and there is a vast literature on potential defaults including uniform priors, Jeffreys’ priors, reference priors, maximum entropy priors, and weakly informative priors. These methods, however, often manifest a key conceptual tension in prior modeling: a model encoding true prior information should be chosen without reference to the model of the measurement process, but almost all common prior modeling techniques are implicitly motivated by a reference likelihood. In this paper we resolve this apparent paradox by placing the choice of prior into the context of the entire Bayesian analysis, from inference to prediction to model evaluation.

Does quantum uncertainty have a place in everyday applied statistics

We are sympathetic to the general ideas presented in the article by Pothos & Busemeyer (P&B): Heisenbergs uncertainty principle seems naturally relevant in the social and behavioral sciences, in which measurements can affect the people being studied. We propose that the best approach for developing quantum probability models in the social and behavioral sciences is not by directly using the complex probability-amplitude formulation proposed in the article, but rather, more generally, to consider marginal probabilities that need not be averages over conditionals.

Stan-Dev/Cmdstan V2.17.0

v2.17.0nCmdStan release notesnMost of the changes are due to improvements in the Stan and Math libraries.nSee the release notes for Stan v2.16.0 and Math v2.16.0 for more details.nDownload instructionsn Note: Download using the links to cmdstan-2.16.0.tar.gz or cmdstan-2.16.0.zip for a version that includes Stan and all libraries. (The Source code downloads does not include the Stan library and will not work as-is.)nTo clone CmdStan using git, see: https://github.com/stan-dev/cmdstan/wiki/Getting-Started-with-CmdStan