lrstat (version 0.3.3)

fadjpdun: Adjusted p-Values for Dunnett-Based Graphical Approaches

Description

Obtains the adjusted p-values for graphical approaches using weighted Dunnett tests.

Usage

fadjpdun(p, wgtmat = NULL, family = NULL, corr = NULL, nthreads = 0)

Value

A list with the following components:

• inthyp: The indicator matrix for the intersection hypotheses.

• pinter: The local p-values for the intersection hypotheses.

• padj: The adjusted p-values for the elementary hypotheses.

Arguments

p

The raw p-values for elementary hypotheses.

wgtmat

A list containing the weight matrix and the indicator matrix for intersection hypotheses. If NULL, equal weights are assigned within each intersection hypothesis.

family

The matrix of family indicators for elementary hypotheses. Defaults to one family containing all elementary hypotheses.

corr

The correlation matrix that should be used for the parametric test. Can contain NAs for unknown correlations between families. By default, within-family correlations are 0.5 and between-family correlations are missing.

nthreads

The number of threads to use in simulations (0 means the default RcppParallel behavior).

Author

Kaifeng Lu,

References

Frank Bretz, Martin Posch, Ekkehard Glimm, Florian Klinglmueller, Willi Maurer, and Kornelius Rohmeyer. Graphical approach for multiple comparison procedures using weighted Bonferroni, Simes, or parameter tests. Biometrical Journal. 2011; 53:894-913.

Examples

pvalues <- matrix(c(0.01,0.005,0.015,0.022, 0.02,0.015,0.010,0.023),
                  nrow=2, ncol=4, byrow=TRUE)
w <- c(0.5,0.5,0,0)
G <- matrix(c(0,0,1,0,0,0,0,1,0,1,0,0,1,0,0,0),
            nrow=4, ncol=4, byrow=TRUE)
wgtmat <- fwgtmat(w,G)

family <- matrix(c(1,1,0,0,0,0,1,1), nrow=2, ncol=4, byrow=TRUE)
corr <- matrix(c(1,0.5,NA,NA, 0.5,1,NA,NA,
                NA,NA,1,0.5, NA,NA,0.5,1),
              nrow = 4, byrow = TRUE)
fadjpdun(pvalues, wgtmat, family, corr, nthreads = 1)