DiscreteFDR: FDR-based Multiple Testing Procedures with Adaptation for...

In DISOhda/DiscreteFDR: FDR Based Multiple Testing Procedures with Adaptation for Discrete Tests

FDR-based Multiple Testing Procedures with Adaptation for Discrete Tests

Description

This package implements the [HSU], [HSD], [AHSU], [AHSD] and [HBR-\lambda] procedures for discrete tests (see References).

Details

The functions are reorganized from the reference paper in the following way. discrete.BH() (for Discrete Benjamini-Hochberg) implements [HSU], [HSD], [AHSU] and [AHSD], while DBR() (for Discrete Blanchard-Roquain) implements [HBR-\lambda]. DBH() and ADBH() are wrapper functions for discrete.BH() to access [HSU] and [HSD], as well as [AHSU] and [AHSD] directly.

This package is part of a package family to which the DiscreteDatasets and DiscreteTests packages also belong. The latter allows to compute p-values and their respective supports for various tests. The objects that contain these results can be used directly by the discrete.BH(), DBH(), ADBH() and DBR() functions. Alternatively, these functions also accept a vector of raw observed p-values and a list of the respective discrete supports of the CDFs of the p-values.

Note: The former function fisher.pvalues.support(), which allows to compute such p-values and supports in the framework of a Fisher's exact test, is now deprecated and should not be used anymore. It has been replaced by generate.pvalues().

The same applies for the function fast.Discrete(), which is a wrapper for fisher.pvalues.support() and discrete.BH() and allows to apply discrete procedures directly to a data set of contingency tables and perform data preprocessing before p-values are computed. It is also now deprecated and has been replaced by direct.discrete.BH(), but for more flexibility, users may employ pipes, e.g.
⁠data |>⁠
⁠ DiscreteDatasets::reconstruct_*(<args>) |>⁠
⁠ DiscreteTests::*.test.pv(<args>) |>⁠
⁠ discrete.BH(<args>)⁠.

Author(s)

Maintainer: Florian Junge [e-mail] (ORCID) [contributor]

Authors:

• Sebastian Döhler [e-mail] (ORCID) [contributor]

• Guillermo Durand (ORCID) [contributor]

Other contributors:

• Etienne Roquain [contributor]

• Christina Kihn [contributor]

References

Döhler, S., Durand, G., & Roquain, E. (2018). New FDR bounds for discrete and heterogeneous tests. Electronic Journal of Statistics, 12(1), pp. 1867-1900. \Sexpr[results=rd]{tools:::Rd_expr_doi("10.1214/18-EJS1441")}

G. Blanchard and E. Roquain (2009). Adaptive false discovery rate control under independence and dependence. Journal of Machine Learning Research, 10, pp. 2837-2871. \Sexpr[results=rd]{tools:::Rd_expr_doi("10.48550/arXiv.0707.0536")}

Döhler, S. (2018). A discrete modification of the Benjamini–Yekutieli procedure. Econometrics and Statistics, 5, pp. 137-147. \Sexpr[results=rd]{tools:::Rd_expr_doi("10.1016/j.ecosta.2016.12.002")}

See Also

Useful links:

• https://github.com/DISOhda/DiscreteFDR

• Report bugs at https://github.com/DISOhda/DiscreteFDR/issues

DISOhda/DiscreteFDR documentation built on April 14, 2025, 8:35 a.m.