qch: Query Composed Hypotheses
Provides functions for the joint analysis of K sets
of p-values obtained for a same list of items. This joint analysis is
performed by querying a composed hypothesis, i.e. an arbitrary complex
combination of simple hypotheses, as described in Mary-Huard et al.
(2021) <arXiv:2104.14601>. The null distribution corresponding to the
composed hypothesis of interest is obtained by fitting non-parametric
mixtures models (one for each of the simple hypothesis of the complex
combination). Type I error rate control is achieved through Bayesian
False Discovery Rate control. The 3 main functions of the package
GetHinfo(), qch.fit() and qch.test() correspond to the 3 steps for
querying a composed hypothesis (composed H0/H1 formulation, inferring
the null distribution and testing the null hypothesis).
||R (≥ 2.10)
||graphics, ks, mclust, stats
||Tristan Mary-Huard <tristan.mary-huard at agroparistech.fr>
Please use the canonical form
to link to this page.