An adaptation of Kernelized Stein Discrepancy, this package provides a goodness-of-fit test of whether a given i.i.d. sample is drawn from a given distribution. It works for any distribution once its score function (the derivative of log-density) can be provided. This method is based on "A Kernelized Stein Discrepancy for Goodness-of-fit Tests and Model Evaluation" by Liu, Lee, and Jordan, available at <http://arxiv.org/abs/1602.03253>.
|Author||Min Hyung Kang [aut, cre], Qiang Liu [aut]|
|Date of publication||2016-07-31 08:53:50|
|Maintainer||Min Hyung Kang <Minhyung.Daniel.Kang@gmail.com>|
|License||MIT + file LICENSE|
demo_gmm: Tests 1-dimensional Gaussian Mixture Models.
demo_gmm_multi: Tests multidimensional Gaussian Mixture Models.
demo_iris: Fits Gaussian Mixture model and computes the KSD value for...
demo_normal_performance: Shows KSD p value change with respect variation in noise
demo_simple_gamma: Tests 1-dimensional Gamma Distribution with customized...
demo_simple_gaussian: Tests 1-dimensional Gaussian Distribution with customized...
gmm: Returns a Gaussian Mixture Model
KSD: Estimate Kernelized Stein Discrepancy (KSD)
likelihoodgmm: Calculates the likelihood for a given dataset for a GMM
perturbgmm: Returns a perturbed model of given GMM
plotgmm: Plots histogram for 1-d GMM given the dataset
posteriorgmm: Calculates the posterior probability for a given dataset for...
rgmm: Generates dataset from Gaussian Mixture Model
scorefunctiongmm: Score function for given GMM : calculates score function...