Multinomial

multinomial.Multinomial(self, alpha, theta_0, k=100)

Sample ratio mismatch test from Lindon and Malek (2022).

• Parent class: Inference
• Example

Parameters

Name	Type	Description	Default
alpha	float	Probability of Type I error \(\alpha\).	required
theta_0	np.ndarray	Null Multinomial parameters \(\mathbf{\theta}_0\).	required
k	float	Concentration for Dirichlet prior parameters \(\mathbf{\alpha}_0 = k \mathbf{\theta}_0\).	100

Attributes

Name	Description
alpha_0	Prior Dirichlet parameters \(\mathbf{\alpha}_0\).
counts	Success counts.
odds	Posterior odds.
theta	Estimate of theta \(\mathbf{\hat{\theta}}\).
theta_0	Null Multinomial parameters \(\mathbf{\theta}_0\).

Methods

Name	Description
update	Update the model with success counts.

update

multinomial.Multinomial.update(x)

Update the model with success counts.

Parameters

Name	Type	Description	Default
x	np.ndarray	Success counts.	required

References

Lindon, Michael, and Alan Malek. 2022. “Anytime-Valid Inference for Multinomial Count Data.” In Advances in Neural Information Processing Systems, edited by Alice H. Oh, Alekh Agarwal, Danielle Belgrave, and Kyunghyun Cho. https://openreview.net/forum?id=a4zg0jiuVi.