
The functions compute CV as well as two robust versions of the CV.
CV(x, na.rm = FALSE)
numeric vector.
logical. Should missing values be removed?
CV value.
The functions compute the (classical) coefficient of variation as well as two robust variants.
medCV
uses the (standardized) MAD instead of SD and median instead of mean.
iqrCV
uses the (standardized) IQR instead of SD and median instead of mean.
C.N.P.G. Arachchige, L.A. Prendergast and R.G. Staudte. Robust analogues to the Coefficient of Variation. https://arxiv.org/abs/1907.01110.
# NOT RUN {
## 5% outliers
out <- rbinom(100, prob = 0.05, size = 1)
sum(out)
x <- (1-out)*rnorm(100, mean = 10, sd = 2) + out*25
CV(x)
medCV(x)
iqrCV(x)
# }
Run the code above in your browser using DataLab