Three ways to calculate correlation in R. Basics of the common correlation statistic (pearson/kendall/spearman), the newer distance correlation statistic (Brownian distance covariance) and the ever newer maximal information coefficient (a maximal information-based nonparametric exploration (MINE) statistic) in R

3-correlation-methods.R

# three correlation methods

duration = faithful$eruptions   # the eruption durations 
waiting = faithful$waiting      # the waiting period
plot(duration, waiting) 

cor(duration, waiting) 
cor.test(duration, waiting) 

# distance correlation statistic
library("energy")
dcor(duration, waiting) 
dcov.test(duration, waiting) 

# maximal information coefficient 
# http://www.exploredata.net/Usage-instructions
# download MINE.jar and MINE.r
# see here if problems with rJava
# http://stackoverflow.com/q/2399027/1036500
setwd("C:/Users/marwick/Downloads")
source("MINE.R")
rMINE(t(cbind(duration, waiting)), "matrix", 'all.pairs')