Outlier removal in R with MAD criterion: equations taken from [Leys et al (2013)](http://www.sciencedirect.com/science/article/pii/S0022103113000668).

outlierRemoval.R

require(plyr)
require(dplyr)

data.outliersRemoved<-ddply(data, .(withinIV1, withinIV2), function(d){
  limits.outliers = median(d$DV) + 2.5*c(-1, 1)*mad(d$DV))
  d$DV[which(((d$DV - limits.outliers[1])*(limits.outliers[2] - d$DV)) <= 0)]<-NA
  return(d)
})