Estimated standard deviation of the location estimator mu
disper
M-scale/dispersion estimate
Arguments
x
a vector of univariate observations
psi
a string indicating which score function to use. Valid options are "bisquare", "huber",
"opt" and "mopt".
eff
desired asymptotic efficiency. Valid options are 0.85, 0.9 and 0.95 (default) when
psi = "bisquare" or "huber", and 0.85, 0.9, 0.95 (default) and 0.99 when
psi = "opt" or "mopt".
maxit
maximum number of iterations allowed.
tol
tolerance to decide convergence of the iterative algorithm.
na.rm
a logical value indicating whether NA values should be stripped before
the computation proceeds. Defaults to FALSE
set.seed(123)
r <- rnorm(150, sd=1.5)
locScaleM(r)
# 10% of outliers, sd of good points is 1.5set.seed(123)
r2 <- c(rnorm(135, sd=1.5), rnorm(15, mean=-10, sd=.5))
locScaleM(r2)