CompetingRiskFrailtySurvfitControl {CompetingRiskFrailty}R Documentation

Control Values for Fitting of Competing Risks with Frailties Model

Description

The values supplied in the call of 'CompetingRiskFrailtySurvfitCreate' function will replace the defaults, and a list with all possible arguments is returned. The returned list is used as the 'control' argument to the 'CompetingRiskFrailtySurvfitCreate' function.

Usage

CompetingRiskFrailtySurvfitControl(niter.EM=50, niter.epoch = 2, tol.epoch = 1e-08, tol.variance = 1e-08,
                                   tol.frailty = 1e-06, print.penalty.mixture=TRUE,print.EM=TRUE,
				   print.estimates=FALSE,print.log.lik=TRUE,...)

Arguments

niter.EM

maximum number of the (outer) EM-iterations.

niter.epoch

maximum number of the (inner) iterations in optimization for varying coefficients parameters theta and penalty parameters of their random parts, within an EM-iteration.

tol.epoch

tolerance for the convergence criterion for the fixed and random parameters of the varying coefficients.

tol.variance

tolerance for the convergence criterion for the penalty values of varying coefficients.

tol.frailty

tolerance for the the convergence criterion for the frailty terms.

print.penalty.mixture

logical value for printing the value of the penalty parameter from the specified grid of values.

print.EM

logical value for printing the current number of an EM-itertion.

print.estimates

logical value for printing the estimates of the fixed parameters theta and penalties of varying coefficients after the last EM-iteration.

print.log.lik

logical value for printing the marginal log likelihood of the model in each EM-iteration.

...

other parameters which can only be: 'num.knots' for the number of spline knots for survival time. If specified it is a vector of integer values of the length equal to the number of competing risks. If not specified, the optimal values will be defined internally.

Details

The defaults or user specified values are applied as the 'control' argument in the call of the 'CompetingRiskFrailtySurvfitCreate' function. It can be an (empty) list object or a call to the 'CompetingRiskFrailtySurvfitControl' function itself, whether or not with supplied arguments to be changed from their default values.

Value

a list with components for each of the possible arguments.

Author(s)

Pavel Khomski <pkhomski@wiwi.uni-bielefeld.de>

References

Kauerman G. and Khomski P. (2006). Full time or part time reemployment: a competing risk model with frailties and smooth effects using a penalty based approach, to appear.

See Also

CompetingRiskFrailtySurvfitCreate


[Package CompetingRiskFrailty version 2.0 Index]