addreg.control {addreg} | R Documentation |
Auxiliary function for addreg
fitting.
Typically only used internally by nnpois
and
nnnegbin
, but may
be used to construct a control
argument to these functions.
addreg.control(bound.tol = 1e-06, epsilon = 1e-10, maxit = 10000, trace = 0)
bound.tol |
positive tolerance specifying the
interior of the parameter space. If the fitted model is
more than |
epsilon |
positive convergence tolerance
ε; the estimates are considered to have
converged when √{
∑ (θ_{old} - θ_{new})^2} / √ {∑
θ_{old}^2} < ε, where θ is the
vector of parameter estimates. See |
maxit |
integer giving the maximum number of EM algorithm iterations for a given parameterisation. |
trace |
number indicating level of output that should be produced. >= 1 gives output for each parameterisation, >= 2 gives output at each iteration. |
This is used similarly to glm.control
. The
control
argument of addreg
is by
default passed to the control
argument of
nnpois
or nnnegbin
.
When trace
is greater than zero, calls to
cat
produce the output. Hence,
options(digits = *)
can be used to increase
the precision.
A list with components named as the arguments.
Mark W. Donoghoe markdonoghoe@gmail.com
glm.control
, the equivalent function for
glm
fitting.
nnpois
and nnnegbin
, the
functions used to fit addreg
models.
## Variation on example(glm.control) : counts <- c(18,17,15,20,10,20,25,13,12) outcome <- gl(3,1,9) treatment <- gl(3,3) oo <- options(digits = 12) addreg.D93X <- addreg(counts ~ outcome + treatment, family = poisson, trace = 2, epsilon = 1e-2) options(oo) coef(addreg.D93X)