Package 'ClusterRankTest'

Rank Tests for Clustered Data

Description

This package consists of methods that compute rank based tests for clustered data.

Details

Package:	ClusterRankTest
Type:	Package
Version:	1.0
Date:	2016-04-21
License:	GPL-2 | GPL-3

Author(s)

Sandipan Dutta, Somnath Datta

Maintainer: Sandipan Dutta <[email protected]>

---

Cluster Rank Test

Description

This package consists of methods that compute rank based tests for clustered data.

Usage

clus.rank.sum(Cluster, X, grp = NULL, Y = NULL, test = c("DS", "DD", "SDS"))

Arguments

Cluster	Cluster ID
X	Outcome variable
grp	Binary group indicator variable (0 or 1) if test= "DS" or "DD"
Y	Matched outcome variable if test="SDS"
test	"DS" =Datta-Satten rank-sum test, "DD" = Dutta-Datta rank-sum test, "SDS" = Data-Satten signed rank test

Value

pvalue	P-value for the test
Test Statistic	Test statistic value for the test

References

Datta, S., and Satten, G. A. (2005). Rank-sum tests for clustered data. Journal of the American Statistical Association, 100, 908-915.

Datta, S., and Satten, G. A. (2008). A Signed-rank test for clustered data. Biometrics, 64, 501-507.

Dutta, S., and Datta, S. (2015). A rank-sum test for clustered data when the number of subjects in a group within a cluster is informative. Biometrics, doi: 10.1111/biom.12447.

Examples

Cluster<-c(1,1,2,2,2,2,3,3,3)
X<-c(1,4,2,4,6,7,4,7,8)
grp<-c(0,1,0,0,1,1,1,0,1)
dataset <- list(Cluster,X,grp)

 clus.rank.sum(Cluster, X, grp, test="DS")

---

dataset

Description

The dataset has three columns. The first two columns will be 'Cluster ID' and 'X'(outcome). The third column will be either 'Group Indicator' (for rank-sum tests) or 'Y'(paired outcome for signed-rank tests).

Usage

data("dataset")

---

Print function.

Description

Prints the p-value and the test statistic.

---