rgsOptIC.Ms: Computation of the optimally robust IC for Ms estimators

In RobRex: Optimally Robust Influence Curves for Regression and Scale

Computation of the optimally robust IC for Ms estimators

Description

The function rgsOptIC.Ms computes the optimally robust conditionally centered IC for Ms estimators in case of linear regression with unknown scale and average conditional (convex) contamination neighborhoods where the regressor is random; confer Subsection 7.3.2 of Kohl (2005).

Usage

rgsOptIC.Ms(r, K, a1.x.start, a3.start = 0.25, b.sc.start = 1.5, 
             bUp = 1000, ggLo = 0.5, ggUp = 1, delta = 1e-06, 
             itmax = 1000, check = FALSE)

Arguments

r	non-negative real: neighborhood radius.
K	object of class "DiscreteDistribution"
ggLo	positive real: the lower end point of the interval to be searched for \gamma.
ggUp	positive real: the upper end point of the interval to be searched for \gamma.
a1.x.start	real: starting value for the Lagrange multiplier function \alpha_1(x).
a3.start	real: starting value for Lagrange multiplier \alpha_3.
b.sc.start	positive real: starting value for the clipping bound b_{\rm sc}.
bUp	positive real: the upper end point of the interval to be searched for b.
delta	the desired accuracy (convergence tolerance).
itmax	the maximum number of iterations.
check	logical. Should constraints be checked.

Value

Object of class "CondIC"

Author(s)

Matthias Kohl [e-mail]

References

Kohl, M. (2005) Numerical Contributions to the Asymptotic Theory of Robustness. Bayreuth: Dissertation.

See Also

CondIC-class

Examples

## code takes some time
## Not run: 
K <- DiscreteDistribution(1:5) # = Unif({1,2,3,4,5})
IC1 <- rgsOptIC.Ms(r = 0.1, K = K)
checkIC(IC1)
Risks(IC1)

## End(Not run)

RobRex documentation built on Jan. 29, 2024, 3:01 a.m.