Umpire (version 2.0.11)

SurvivalModel-class: The "SurvivalModel" Class

Description

A SurvivalModel class represents the information for simulating survival times for each patient.

Usage

SurvivalModel(baseHazard = 1/5,
              accrual = 5,
              followUp = 1,
              units = 12,
              unitName = "months")
# S4 method for SurvivalModel
rand(object, n, beta = NULL, ...)

Value

The SurvivalModel generator returns an object of class

SurvivalModel.

The rand method returns a data.frame with components:

LFU

time to event

Event

whether the data is censored

Arguments

baseHazard

numeric scalar describing the underlying hazard rate at baseline levels of covariates

accrual

numeric scalar representing number of patient accrual years

followUp

numeric scalar representing length of follow up, in years

units

numeric scalar representing number of units per year where units are specified by unitName

unitName

character string representing the unit argument type

object

object of class SurvivalModel

n

numeric scalar specifying quantity of random numbers

beta

numeric vector specifying beta parameters for patients

...

extra arguments for generic routines

Objects from the Class

Although objects of the class can be created by a direct call to new, the preferred method is to use the SurvivalModel generator function.

Slots

baseHazard:

see corresponding argument above

accrual:

see corresponding argument above

followUp:

see corresponding argument above

units:

see corresponding argument above

unitName:

see corresponding argument above

Methods

rand(object, n, beta, ...)

Simulate survival data for n patients given beta.

Author

Kevin R. Coombes , Jiexin Zhang ,

References

Zhang J, Coombes KR.
Sources of variation in false discovery rate estimation include sample size, correlation, and inherent differences between groups.
BMC Bioinformatics. 2012; 13 Suppl 13:S1.

See Also

CancerModel

Examples

showClass("SurvivalModel")
sm <- SurvivalModel()
## Generate data from base model
outcome <- rand(sm, 100)
summary(outcome)
## Generate data from five classes with different beta parameters
beta <- rep(rnorm(5, 0, 2), each = 20)
outcome <- rand(sm, 100, beta = beta)
summary(outcome)