Compute the M-estimate of scale using the MAD as initial estimate.
mscale(
x,
delta = 0.5,
rho = c("bisquare", "huber", "gauss"),
cc,
eps = 1e-08,
maxit = 200
)Numeric vector of length one containing the solution s_n to
the equation above.
numeric vector.
desired value for the right-hand side of the M-estimation equation.
rho function to use in the M-estimation equation. Valid options
are bisquare, huber and gauss.
non-negative constant for the chosen rho function. If missing, it will be
chosen such that the expected value of the rho function under the normal model
is equal to delta.
threshold for convergence. Defaults to 1e-8.
maximum number of iterations. Defaults to 200.
This solves the M-estimation equation given by $$\sum_{i=1}^n \rho( x_i / s_n; cc ) = n delta$$
All NA values in x are removed before calculating the scale.