Find multivariate outliers using Mahalanobis Distances

TERR_Expression_Function_Mahalanobis_Outlier.r

########################################################
# Takes an arbitrarily long list of input columns and 
# returns a boolean indicating whether or not each row 
# is an outlier. 
#
# The function uses the critical value for Mahalanobis 
# Distance calculated from an upper tailed ChiSq 
# distribution with p=0.001.
########################################################

# create vector of inputs
inputs <- grep("^input[0-9]+$",ls(), value = TRUE)

# capture columns as a matrix
x <- sapply(inputs, function(y) {eval(parse(text = y))})

# find complete cases
cc <- complete.cases(x)

# column of complete cases
xcc <- x[cc,]

# column of Mahalanobis Dists
dists <- rep(NA, nrow(x))
dists[cc] <- mahalanobis(xcc, colMeans(xcc), cov(xcc))

# column of critical values
critical <- rep(qchisq(0.001, df=ncol(xcc)-1, lower.tail = FALSE), nrow(x))

# column of outliers
outlier <- dists >= critical

# capture the output
output <- outlier