bhmControl {bhm}

Auxiliary function for bhm fitting

Description

Auxiliary function for bhm fitting. Typically only used internally by 'bhmFit', but may be used to construct a control argument to either function.

Usage

  bhmControl(method = 'Bayes', interaction, biomarker.main, alpha, 
               B, R, thin, epsilon, c.n, beta0, sigma0)

Arguments

method

choose either ‘Bayes’ for Bayes method with MCMC or ‘profile’ for profile likelihood method with Bootstrap. The default value is 'Bayes'

interaction

an option of fitting model with interaction term When interaction = TRUE, a predictive biomarker model will be fitted When interaction = FALSE, a prognostic biomarker model will be fitted The default value is interaction = TRUE.

biomarker.main

include biomarker main effect, default is TRUE

B

number of burn in

R

number of replications for Bayes meothd or number of Bootstrap for profile likelihood method

thin

thinning parameter for Gibbs samples, default is 2

epsilon

biomarker (transformed) step length for profile likelihood method, default is 0.01

alpha

significance level (e.g. alpha=0.05)

c.n

number of threshold (i.e. the cut point), default is 1

beta0

initial value for mean of the prior distribution of beta, default is 0

sigma0

initial value for variance of the prior distribution of beta, default is 10000

Details

Control is used in model fitting of "bhm".

Value

This function checks the internal consisitency and returns a list of value as inputed to control model fit of bhm.

Note

Based on code from Tian Fang.

Author(s)

Bingshu E. Chen

See Also

bhm

Examples

## To fit a prognostic model for biomarker with two cut-points, 
## 500 burn-in samples and 10000 Gibbs samples,

ctl = bhmControl(interaction = FALSE, B = 500, R = 10000, c.n = 2)

##
## then fit the following model
##
#  fit = bhmFit(x, y, family = 'surv', control = ctl)
##