seg.control {segmented} | R Documentation |
Auxiliary function as user interface for 'segmented' fitting. Typically
only used when calling any 'segmented' method (segmented.lm
or segmented.glm
).
seg.control(toll = 1e-04, it.max = 20, display = FALSE, last = TRUE, maxit.glm = 25, h = 1)
toll |
positive convergence tolerance. |
it.max |
integer giving the maximal number of iterations. |
display |
logical indicating if output should be produced for each iteration. |
last |
logical indicating if output should include only the last fitted model. |
maxit.glm |
integer giving the maximum number of inner IWLS iterations (see details). |
h |
positive factor (from zero to one) modifying the increments in breakpoint estimation (see details). |
Fitting a `segmented' model is attained via fitting iteratively standard GLMs. The number of iteration is
governed by it.max
, while the (maximum) number of (inner) iterations to fit the GLM at each outer
iteration is fixed via maxit.glm
. Usually three-four inner iterations may be sufficient.
If last=TRUE
, the object resulting from segmented.lm
(or segmented.glm
) is a
list of fitted GLM; the i-th model is the segmented model with the values of the breakpoints at the i-th iteration.
Sometimes to stabilize the procedure, it can be useful to set h<1
to reduce the increments in the breakpoint estimation. At each
iteration the updated estimate is usually given by psi.new=psi.old+increm
. By setting h<1
(actually min(abs(h),1)
is considered) causes the following alterations to the algorithm:
(i) the actual maximum number of iterations is increased up to it.max+round(it.max/2)
and
(ii) the breakpoint update is computed via psi.new=psi.old+h*increm
after the it.max
th iteration.
A list with the arguments as components.
#decrease the maximum number inner iterations and display the #evolution of the (outer) iterations seg.control(display = TRUE, maxit.glm=4)