Learn R Programming

MCARtest (version 1.2.1)

Optimal Nonparametric Testing of Missing Completely at Random

Description

Provides functions for carrying out nonparametric hypothesis tests of the MCAR hypothesis based on the theory of Frechet classes and compatibility. Also gives functions for computing halfspace representations of the marginal polytope and related geometric objects.

Copy Link

Version

Install

install.packages('MCARtest')

Monthly Downloads

604

Version

1.2.1

License

MIT + file LICENSE

Maintainer

Thomas Berrett

Last Published

March 22nd, 2024

Functions in MCARtest (1.2.1)

Calculate the H-representation of the marginal polytope

Carry out a test of MCAR in a contingency table, given incomplete observations.

Carry out Little's test of MCAR

A function computing the incompatibility index

Compute the columnwise average of means/variances

Computes the sequence of patterns, means, variances, covariance and correlation matrices for a given dataset with missing values.

Computes an inconsistency index for sequences of variances.

Compute the log likelihood of a probability mass function, under MCAR, given complete and incomplete data

MCAR_meancovTest

Carry out a test of MCAR using first and second moments.

Compute the MLE under MCAR in a contingency table using the EM algorithm, given complete and incomplete observations.

A function computing the incompatibility index and associated closest joint mass function using the dual formulation

Calculates the total cardinality of the sample spaces.

Generates the column indices used internally to generate the sparse matrix A.

Calculates the individual cardinalities of the sample spaces.

A function indexing the rows of A

A function indexing the columns of A

Internal function multiplying a mass function by the sparse matrix A.

Compute the log likelihood of a probability mass function, without assuming MCAR, given complete and incomplete data

A function computing the incompatibility index for sequences of correlation matrices

Generate the matrix A, whose columns are the vertices of the marginal polytope.

Calculate the critical value for our improved test

Carry out Fuchs's test of MCAR in a contingency table, given complete and incomplete observations.

EquivalenceClass

Simplifies H-representation by exploiting symmetry

Generate the matrix A, whose columns are the vertices of the marginal polytope, as a sparse matrix.

InconsMinkSumHrep

Calculate the H-representation of the general (possibly inconsistent) Minkowski sum

Computes an inconsistency index for sequences of means.

ConsMinkSumHrep

Calculate the H-representation of the consistent Minkowski sum

Calculate the critical value for our simple test

Perform one step of the EM algorithm for finding the MLE under MCAR in a contingency table.

aMatrixSparseRevLex

Generates the row indices used internally to generate the sparse matrix A.

Round errors in halfspace representations