bootstrapMI: Calculate bootstrap p-values for mutual information (MI) measures

Description

This function takes a numerical matrix (or two vectors) and calculates bootstrapped (by permutation) p-values to test if the mutual information value is equal to zero. If the first argument is a matrix, the p-values are calculated between all pairs of rows of the matrix.

Usage

bootstrapMI(x, y=NULL, bRep, ret="p-value")

Arguments

numerical matrix or vector to be analysed. If a vector, the argument y must be informed.

numerical vector. Must be informed if x is a vector. If x is a matrix, this argument is ignored. Defaults to NULL.

bRep

number of permutation to be done in the test.

ret

character string with the value to return. Must be 'p-value' (default) for the usual p-value or 'max', to return the maximum absolute correlation value obtained by the permutation.

Value

The result of this function is a square matrix (length equal to the number of rows of x) if x is a matrix or a numerical value if x and y are vectors. The result is the p-values or maximum MI values calculated by permutation tests.

Details

The method implemented in this function is proposed by Butte and Kohane (2000). The MI value is calculated using the function MI.

References

Butte, A.J. and Kohane, I.S. Mutual information relevance networks: functional genomic clustering using pairwise entropy measurements. In Pacific Symposium on Biocomputing, 5, 415-426, 2000 (http://psb.stanford.edu/psb-online/proceedings/psb00/)

Examples

Run this code

x <- runif(50, 0, 1)
y <- rbeta(50, 1, 2)
bootstrapMI(x, y, bRep=100)

z <- matrix(rnorm(100, 0, 1), 4, 25)
bootstrapMI(z, bRep=100)

Run the code above in your browser using DataLab