Distance and Correlation

distance_correlation.md

Distance and Correlation

References:

• http://www.analytictech.com/mb876/handouts/distance_and_correlation.htm
• http://bioconductor.org/help/publications/books/bioinformatics-and-computational-biology-solutions/

Code:

standardize <- function(z) {
  rowmed <- apply(z, 1, median)
  rowmad <- apply(z, 1, mad)
  rv <- sweep(z, 1, rowmed)
  rv <- sweep(rv, 1, rowmad, "/")
  return(rv)
}

x <- data.frame(A = rnorm(10), B = rnorm(10) * 20)

cor(x)
           A          B
A  1.0000000 -0.6746946
B -0.6746946  1.0000000

cor(standardize(x))
   A  B
A  1 -1
B -1  1

dist(t(x))
         A
B 88.64185

dist(t(standardize(x)))
         A
B 4.265854