API Documentation#

Sampling states from the selection event#

Sampling(sampling_algorithm)

Class allowing to sample states in the selection event using the Rejection Sampling method (RS) or the Simulated Annealing algorithm (SA).

Bunch of useful functions#

Visualizing results#

PSI Methods#

PSILOGIT.Methods:

PSILOGIT.Methods.Weak:

Weak()

This weak learner is a two-sided test based on the statistic \(\sum_{i=1}^n |\overline \pi_i^{\theta_0} - y_i|\) where \(\overline \pi^{\theta_0}\) is the expectation of the vector of observations under the null conditional to the selection event.

PSILOGIT.Methods.Sigle:

Sigle()

Class implementing the Post-Selection Inference procedure proposed with the SIGLE method in both the selected and the saturated model.

PSILOGIT.Methods.Taylor:

Taylor()