CorrBin-package {CorrBin}

Nonparametrics for Correlated Binary and Multinomial Data

Description

This package implements nonparametric methods for analyzing exchangeable binary and multinomial data with variable cluster sizes with emphasis on trend testing. The input should specify the treatment group, cluster-size, and the number of responses (i.e. the number of cluster elements with the outcome of interest) for each cluster.

Details

• The CBData/CMData and read.CBData/read.CMData functions create a ‘CBData’ or ‘CMData’ object used by the analysis functions.

• ran.CBData and ran.CMData can be used to generate random binary or multinomial data using a variety of distributions.

• mc.test.chisq tests the assumption of marginal compatibility underlying all the methods, while mc.est estimates the distribution of the number of responses under marginal compatibility.

• Finally, trend.test performs three different tests for trend along the treatment groups for binomial data.

Author(s)

Aniko Szabo

Maintainer: Aniko Szabo <[e-mail]>

References

Szabo A, George EO. (2009) On the Use of Stochastic Ordering to Test for Trend with Clustered Binary Data. Biometrika

Stefanescu, C. & Turnbull, B. W. (2003) Likelihood inference for exchangeable binary data with varying cluster sizes. Biometrics, 59, 18-24

Pang, Z. & Kuk, A. (2007) Test of marginal compatibility and smoothing methods for exchangeable binary data with unequal cluster sizes. Biometrics, 63, 218-227