coxaalen.control: Control a Cox-Aalen model fit

Description

Set parameters controlling the model fit returned by coxaalen.

Usage

coxaalen.control(eps = 1e-07, eps.norm = c("max", "grad"), iter.max = 5000, armijo = 1/3, var.coef = TRUE, coef.typ = 1, coef.max = 10, trace = FALSE, thread.max = 1, data = FALSE)

Arguments

eps

threshold value for the norm used to measure convergence in the parameter estimates.

eps.norm

a character string identifying the norm to use in the convergence criteria---either the maximum norm between the current and previous parameter values (eps.norm = "max") or the absolute inner product between the current value and the score (eps.norm = "grad").

iter.max

maximum number of iterations to attempt. This ensures that coxaalen will eventually exit, even when the convergence criteria is not met. A warning is issued whenever the estimation routine has stopped before converging on a final parameter value.

armijo

a scale factor in (0, 1/2) for Armijo's (1966) rule---a line search used to ensure that each iteration achieves an adequate increase in the log-likelihood. The model fit is typically not very sensitive to this value.

var.coef

a logical value indicating that standard errors for the multiplicative regression coefficients should be estimated. This is done via profile likelihood---an approach that can require an inordinate amount of processing time under many regression coefficients and larger sample size.

coef.typ

a scalar or vector of typical (absolute) values for the multiplicative regression coefficient.

coef.max

a scalar or vector of probable upper bounds for the multiplicative regression coefficient. This and the coef.typ arguments tune variance estimation via the curvature in the profile log-likelihood.

trace

a logical value indicating that CPLEX should print its results to the screen.

thread.max

maximum number of CPU threads to allocate to CPLEX. The default value disables multithreading. A value of zero allows CPLEX to set the number of threads automatically. The actual number of threads used is limited by the number of available processors and the CPLEX license.

data

a logical value indicating that the object returned by coxaalen should contain an element data that gives the maximal intersections and the model matrix split into multiplicative and additive terms.

Value

A list of the above arguments with their final values.

References

Boruvka, A. and Cook, R. J. (2015) A Cox-Aalen model for interval-censored data. Scandinavian Journal of Statistics 42, 414--426.

Armijo, L. (1966) Minimization of functions having Lipschitz continuous first partial derivatives. Pacific Journal of Mathematics 16, 1--3.

Examples

Run this code

if (is.loaded("coxaalen", "coxinterval"))
coxaalen(Surv(left, right, type = "interval2") ~ prop(treat),
         data = cosmesis, control = coxaalen.control(iter.max = 2,
         trace = TRUE))