The hardware and bandwidth for this mirror is donated by dogado GmbH, the Webhosting and Full Service-Cloud Provider. Check out our Wordpress Tutorial.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]dogado.de.

multChernoff

This package computes a finite-sample tail bound of the likelihood ratio test (LRT) under multinomial sampling. The tail bounds can be used to obtain conservative p-values and critical values. This is useful for inference when the sample size is comparable to or even smaller than the alphabet size, where the standard chi-square asymptotic (Wilks’ theorem) may not hold.

Installation

You can install the package from CRAN with

> install.packages("multChernoff")

or from GitHub with

> devtools::install_github("richardkwo/multChernoff")

Usage

Please refer to the vignette.

> vignette("multChernoff")

The package can be used with the finite-sample critical value criticalValue to construct a convex confidence region on the underlying probability vector.

Reference

The method is based on the following work:

F. Richard Guo and Thomas S. Richardson, “Chernoff-Type Concentration of Empirical Probabilities in Relative Entropy,” in IEEE Transactions on Information Theory, vol. 67, no. 1, pp. 549-558, Jan. 2021.

These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.
Health stats visible at Monitor.