Increase maximum number of iterations in lmrob

Question

How do you increase the maximum number of iterations (i.e., the maxit.scale parameter) in the lmrob function in the robustbase package in R?

The default is 200, but I want to increase it.

Answer 1

library(robustbase)
data(starsCYG, package="robustbase")
a1<-lmrob.control()
RlmST<-lmrob(log.light~log.Te,data=starsCYG,control=a1)

Increase maxit.scale; it's not really clear from your question which one of the iteration counts breaks you want to increase, but I suppose it's maxit.scale since it's the only one that is set to 200 by default. Here I increase maxit.scale to 201:

a1$maxit.scale<-201
RlmST<-lmrob(log.light~log.Te,data=starsCYG,control=a1)

Anyway, you can change the other in pretty much the same way: check:

?lmrob.control

Answer 2

It might help if you said you were using the robustbase package.

?lmrob would bring up a help page, and reading it points to lmrob.control which looks like

lmrob.control(setting, seed = NULL, nResample = 500,
              tuning.chi = NULL, bb = 0.5, tuning.psi = NULL,
              max.it = 50, groups = 5, n.group = 400,
              k.fast.s = 1, best.r.s = 2,
              k.max = 200, maxit.scale = 200, k.m_s = 20,
              refine.tol = 1e-7, rel.tol = 1e-7, solve.tol = 1e-7,
              trace.lev = 0,
              mts = 1000, subsampling = c("nonsingular", "simple"),
              compute.rd = FALSE, method = "MM", psi = "bisquare",
              numpoints = 10, cov = NULL,
              split.type = c("f", "fi", "fii"), fast.s.large.n = 2000, ...)

with the detail

k.fast.s (for the fast-S algorithm): Number of local improvement steps (“I-steps”) for each re-sampling candidate.

k.m_s (for the M-S algorithm): specifies after how many unsucessful refinement steps the algorithm stops.

best.r.s (for the fast-S algorithm): Number of of best candidates to be iterated further (i.e., “refined”); is denoted t in Salibian-Barrera & Yohai(2006).

k.max (for the fast-S algorithm): maximal number of refinement steps for the “fully” iterated best candidates.

maxit.scale integer specifying the maximum number of C level find_scale() iterations.

so you presumably want to change one of these.