survMisc (version 0.4.2)

genDfSurv: Generate data frame for survival analysis

Description

Generates a data frame with a binary outcome (events), times and optional predictor variables. An optional coxph model is fitted to the data. Model is fitted with survival::coxph()

Usage

genDfSurv(f = 0, b = 2, c = 1, n = 100, pb = 0.5, nf = 3,
    rc = 0.8, pe = 0.5, t0 = 1, tmax = 100,
    asFactor = FALSE, model = TRUE, timelim = 5)

Arguments

b

binomial predictors, the number of predictors which are binary, i.e. limited to 0 or 1

f

factors, the number of predictors which are factors

c

continuous predictors, the number of predictors which are continuous

n

number of observations in the data frame

nf

the no. of levels in a factor

pb

probability for binomnial predictors the probability of binomial predictors being =1. E.g. if pb=0.3, 30% will be 1s, 70% will be 0s

rc

ratio for continuous variables the ratio of levels of continuous variables to the total number of observations n e.g. if rc=0.8 and n=100, it will be in the range 1-80

pe

probability of event the probability of events (typically death/failure) occurring, i.e. are =1. E.g. if pe=0.5, 50% will be 1s, 50% will be 0s

t0

Lowest (starting) time

tmax

Highest (final) time

asFactor

if TRUE, predictors given as factors will be converted to factors in the data frame before the model is fit

timelim

function will timeout after timelim secs

model

If TRUE will return fitted model

Value

• A list with the following values:
• df
  data frame with predictors (labelled $x1,x2, ..., xn$) and outcome (y), with n rows (observations)
• model
  if model = TRUE model fit with survival::coxph()

Examples

set.seed(1)
genDfSurv()
genDfSurv(b=0, c=2, n=100, pe=0.7)
genDfSurv(b=1, c=0, n=1000)
genDfSurv(f=1, nf=4, b=1, c=0, asFactor=TRUE)