bayesplain.core.gamma_poisson.log_bayes_factor_point_null¶
-
bayesplain.core.gamma_poisson.log_bayes_factor_point_null(events, exposure, rate0, a=
0.5, b=0.0)[source]¶ Log Bayes factor for “the rate is unknown” against “it equals rate0”.
- Parameters:¶
- events : int¶
Events counted.
- exposure : float¶
Exposure.
- rate0 : float¶
The reference rate, per unit of exposure.
- a : float, default 0.5¶
Prior shape.
- b : float, default 0.0¶
Prior rate parameter. When positive, the alternative uses the proper
Gamma(a, b)prior directly and the result is closed form. When zero, the alternative putsBetaPrime(a, a)on the ratio of the rate torate0, so the prior is centred on the reference and carries no units.
- Returns:¶
log(BF10).- Return type:¶