mutualInfo: Mutual Information In Bioconductor-mirror/bioDist: Different distance measures

Description

Calculate mutual information via binning

Usage

 ```1 2``` ```mutualInfo(x, ...) MIdist(x, ...) ```

Arguments

 `x` an n by p matrix or ExpressionSet; if x is an ExpressionSet, then the function uses its 'exprs' slot. `...` arguments passed to `mutualInfo` and `MIdist`: nbinnumber of bins to calculate discrete probabilities; default is 10. diagif TRUE, then the diagonal of the distance matrix will be displayed; default is FALSE. upperif TRUE, then the upper triangle of the distance matrix will be displayed; default is FALSE. samplefor ExpressionSet methods, if TRUE, then distances are computed between samples, otherwise, between genes.

Details

For `mutualInfo` each row of `x` is divided into `nbin` groups and then the mutual information is computed, treating the data as if they were discrete.

For `MIdist` we use the transformation proposed by Joe (1989), delta* = (1 - exp(-2 delta))^.5 where delta is the mutual information. The `MIdist` is then 1-delta*. Joe argues that this measure is then similar to Kendall's tau, `tau.dist`.

Value

An object of class `dist` which contains the pairwise distances.

Robert Gentleman

References

H. Joe, Relative Entropy Measures of Multivariate Dependence, JASA, 1989, 157-164.

`dist`, `KLdist.matrix`, `cor.dist`, `KLD.matrix`
 ```1 2``` ``` x <- matrix(rnorm(100), nrow = 5) mutualInfo(x, nbin = 3) ```