clm.control
Set control parameters for cumulative link models
Set control parameters for cumulative link models
- Keywords
- models
Usage
clm.control(method = c("Newton", "model.frame", "design", "ucminf", "nlminb",
"optim"),
sign.location = c("negative", "positive"),
sign.nominal = c("positive", "negative"),
..., trace = 0L,
maxIter = 100L, gradTol = 1e-06, maxLineIter = 15L, relTol = 1e-6,
tol = sqrt(.Machine$double.eps), maxModIter = 5L,
convergence = c("warn", "silent", "stop", "message"))Arguments
- method
"Newton"fits the model by maximum likelihood and"model.frame"causeclmto return themodel.frame,"design"causesclmto return a list of design matrices etc. that can be used withclm.fit.ucminf,nlminbandoptimrefer to general purpose optimizers.- sign.location
change sign of the location part of the model.
- sign.nominal
change sign of the nominal part of the model.
- trace
numerical, if
> 0information is printed about and during the optimization process. Defaults to0.- maxIter
the maximum number of Newton-Raphson iterations. Defaults to
100.- gradTol
the maximum absolute gradient; defaults to
1e-6.- maxLineIter
the maximum number of step halfings allowed if a Newton(-Raphson) step over shoots. Defaults to
15.- relTol
relative convergence tolerence: relative change in the parameter estimates between Newton iterations. Defaults to
1e-6.- tol
numerical tolerence on eigenvalues to determine negative-definiteness of Hessian. If the Hessian of a model fit is negative definite, the fitting algorithm did not converge. If the Hessian is singular, the fitting algorithm did converge albeit not to a unique optimum, so one or more parameters are not uniquely determined even though the log-likelihood value is.
- maxModIter
the maximum allowable number of consecutive iterations where the Newton step needs to be modified to be a decent direction. Defaults to
5.- convergence
action to take if the fitting algorithm did not converge.
- …
Value
a list of control parameters.