A collection of tools for conducting an imprecise inference is provided. Imprecise prior is used for this inference, and imprecise probability theory introduced by Peter Walley (1991) is its underlying theoretical foundation. The package is developed based on the PhD thesis work of Lee (2014). Poisson and zero-truncated Poisson sampling models are mainly studied with two types of prior distributions.
|Author||Chel Hee Lee [aut, cre, cph], Mikelis Bickis [aut, ths, cph]|
|Date of publication||2015-11-28 14:53:51|
|Maintainer||Chel Hee Lee <firstname.lastname@example.org>|
|License||GPL (>= 2)|
characterize_imprecise_prior: Characterize Imprecise Prior
expected_value_of_imprecise_distribution: Expected Value of Canonical Variable
hyperpara_optim: Objective And Gradient Vector Needed For Optimization
imPois: Imprecise Inferential Framework for Poisson Sampling Model
imprecise_distribution: Imprecise Probability Distribution
imprecise_learning_from_observation: Applying Bayes Rule
kernel_of_imprecise_prob_measure: Kernel of Imprecise Probability Measure Formulated By Bickis...
normalize_imprecise_prob_measure: Comupting Normalizing Constant of Bickis and Lee's...
plot_imprecise_object: Plotting Imprecise Objects
print_imprecise_objects: Print Imprecise Objects
summary_imprecise_object: Summary of 'impinf' object