robmed (version 1.2.1)

cov_control: Tuning parameters for Huber M-estimation of location and scatter

Description

Obtain a list with tuning paramters for cov_Huber().

Usage

cov_control(prob = 0.95, max_iterations = 200, tol = 1e-07)

Value

A list with components corresponding to the arguments.

Arguments

prob

numeric; probability for the quantile of the \(\chi^{2}\) distribution to be used as cutoff point in the Huber weight function (defaults to 0.95).

max_iterations

an integer giving the maximum number of iterations in the iteratively reweighted algorithm.

tol

a small positive numeric value to be used to determine convergence of the iteratively reweighted algorithm.

Author

Andreas Alfons

References

Huber, P.J. (1981) Robust Statistics. John Wiley & Sons.

See Also

cov_Huber()

Examples

data("BSG2014")

# run bootstrap test after winsorization
ctrl <- cov_control(prob = 0.95)
boot <- test_mediation(BSG2014,
                       x = "ValueDiversity",
                       y = "TeamCommitment",
                       m = "TaskConflict",
                       method = "covariance",
                       control = ctrl)
summary(boot)