Skip to contents

The function computes a Matthews correlation coefficient for two factors provided to the function. It assumes each factor is a factor of class labels, and the enteries are paired in order of the vectors.

Usage

mcc(
  x,
  y,
  nperm = 1000,
  nthread = 1,
  alternative = c("two.sided", "less", "greater"),
  ...
)

Arguments

x, y

factor of the same length with the same number of levels

nperm

numeric number of permutations for significance estimation. If 0, no permutation testing is done

nthread

numeric can parallelize permutation texting using BiocParallels bplapply

alternative

indicates the alternative hypothesis and must be one of ‘"two.sided"’, ‘"greater"’ or ‘"less"’. You can specify just the initial letter. ‘"greater"’ corresponds to positive association, ‘"less"’ to negative association.

...

list Additional arguments

Value

A list with the MCC as the $estimate, and p value as $p.value

Details

Please note: we recommend you call set.seed() before using this function to ensure the reproducibility of your results. Write down the seed number or save it in a script if you intend to use the results in a publication.

Examples

x <- factor(c(1,2,1,2,3,1))
y <- factor(c(2,1,1,1,2,2))
mcc(x,y)
#> Warning: The number of levels x and y was different. Taking the union of all class labels.
#> $estimate
#> [1] -0.452267
#> 
#> $p.value
#> [1] 0.442
#>