PriorDB

PriorDB aims to make choosing a prior for a Bayesian model easier. As the prior cannot be understood without the context of the model (Gelman, Simpson, and Betancourt 2017), the first thing to do is choose a model in the sidebar. For each model, the parameters requiring priors are listed, as well as recommended defaults and comparisons between them (if they are available).

Models are broadly grouped by structure and then categorized by properties of the outcome variable.

Contributing

We welcome contributions to PriorDB, we rely on contributions from the community to keep the database up-to-date and accurate. For more information on how to contribute, please see the contribution guidelines. This is the list of the current contributors.

References

Gelman, Andrew, Daniel Simpson, and Michael Betancourt. 2017. “The Prior Can Often Only Be Understood in the Context of the Likelihood.” Entropy 19 (10): 555. https://doi.org/10.3390/e19100555.