Many statistical hypotheses can be formulated in terms of polynomial equalities and inequalities in the unknown parameters and thus correspond to semi-algebraic subsets of the parameter space. We consider large sample asymptotics for the likelihood ratio test of such hypotheses in models that satisfy standard probabilistic regularity conditions. We show that the assumptions of Chernoff's theore...

We link the reverse KL divergence with adversarial learning. This insight enables learning to synthesize realistic samples in two settings: (i) Given a set of samples from the true distribution, an adversarially learned likelihood-ratio and a new entropy bound are used to learn a GAN model, that improves synthesized sample quality relative to previous GAN variants. (ii) Given an unnormalized di...

Objective: To present a geometric ruler to determine predictive values of binary diagnostic test results from prevalence, sensitivity and specificity without calculation. Methods: On logarithmic scale the relationships between pre-/post-test odds and the likelihood ratio as well as sensitivity, speci ficity and the likelihood ratio appear as simple linear (additive) equations. Results: Each of ...

b a c k g r oun d & aim: berg balance scale (bbs) is one of the most applied tests to identify high-risk elderly people for fall. fall is a common health problem among community senior citizens. a diag- nostic test to identify high-risk elderly people can prevent or alleviate falls. the purpose of this study was to determine the accuracy of bbs to predict falls among elderly community dwellers....