bayesplain.priors.ConcentrationPrior¶
-
class bayesplain.priors.ConcentrationPrior(a, name=
'custom', rationale='')[source]¶ A symmetric Dirichlet prior over the cells of a contingency table.
The same preset names as
BetaPrior, resolving to the concentrationathat Gunel and Dickey’s Bayes factors take. The correspondence is exact rather than analogous: for a 2x2 table built from successes and failures, concentrationaon the columns is aBeta(a, a)prior on each group’s rate.Larger values pull the alternative’s predictions toward the null. Jamil et al. (2017) put it well:
a = 10behaves like a flata = 1prior that has already been updated with nine hypothetical observations in every cell.- Variables:¶
Methods
dist()Return
None: a table prior has no one-dimensional density.