ConsMinkSumHrep {MCARtest}

Calculate the H-representation of the consistent Minkowski sum

Description

Computes the minimal halfspace representation of the Minkowski sum of the marginal polytope and the consistent ball defined in Berrett and Samworth (2023).

Usage

ConsMinkSumHrep(bS, M, round = FALSE)

Arguments

bS

A binary matrix specifying the set of observation patterns. Each row encodes a single pattern.

M

A vector of positive integers giving the alphabet sizes of the discrete variables.

round

A logical value indicating whether or not to round coefficients to 15 significant figures. The function RoundErrors can be used separately to substitute other values for 15. Defaults to FALSE.

Value

A halfspace representation object as used by the rcdd package. See Geyer and Meeden (2021) for more detail.

References

Berrett TB, Samworth RJ (2023). “Optimal nonparametric testing of Missing Completely At Random, and its connections to compatibility.” Ann. Statist., 51, 2170–2193.

Geyer CJ, Meeden GD (2021). rcdd: Computational Geometry. https://CRAN.R-project.org/package=rcdd.

Examples

bS=matrix(c(1,1,0, 1,0,1, 0,1,1),byrow=TRUE,ncol=3)
ConsMinkSumHrep(bS,c(2,2,2))