CNVassoc (version 1.4)

simCNVdataWeibull: Simulate of CNV and a right censored Weibull distributed trait

Description

This function simulates intensity for a CNV and a time to event response (followed-up cohort study design) for different scenarios

Usage

simCNVdataWeibull(n, mu.surrog, sd.surrog, w, lambda, shape, time.cens = Inf, cnv.random = FALSE)

Arguments

n

An integer indicating the desired number of individuals to be simulated

mu.surrog

A vector containing the signal (surrogate variable) means for every copy number status (latent classes). Its length must be equal to the number of latent classes

sd.surrog

A vector containing the signal standard deviation for every copy number status. Its length must be equal to mu.surrog.

w

A vector containing the frequencies for every copy number status. Its length must be equal to mu.surrog and its components must sum up one.

lambda

A vector containing the means of the response variable for every copy number status

shape

A vector containing the shape of the response variable for every copy number status

time.cens

Censoring time, e.g. end of follow-up

cnv.random

A logical value. TRUE means that copy number status is drawn under a multinomial distribution with proportions indicated by 'w'. FALSE means that the real simulated frequency is always the same and is rounded to the most similar integer to the frequencies

Value

• Data frame with individual simulated data per row and with the following variables:
• resp
  Time to event or censoring variable (response)
• cens
  Censoring indicator
• surrog
  Signal intensity following a mixture of normals with means, standard deviations and proportions specified by mu.surrog, sd.surrog and w respectively
• cnv
  True copy number status

See Also

simCNVdataBinary, simCNVdataCaseCon, simCNVdataPois, simCNVdataNorm, cnv, CNVassoc

Examples

library(survival)  
maf<-0.3
hr<-1.5
set.seed(123)
simData<-simCNVdataWeibull(n=4000, mu.surrog=c(0,0.5,1), sd.surrog=rep(0.15,3), 
         w=c((1-maf)^2,2*maf*(1-maf), maf^2), lambda=0.05*c(1,hr,hr^2), shape=rep(1,3), time.cens=1.5, cnv.random = FALSE)
CNV<-cnv(simData$surrog,mix.method="EMmixt")
getQualityScore(CNV,type="CNVtools")  
mod<-CNVassoc(Surv(resp, cens)~CNV,data=simData,family="weibull")
CNVtest(mod)
summary(mod)