simdat: Simulated joint longitudinal and survival dataset containing...

Description Usage Format Details See Also

Description

A simulated dataset containing a single continuous longitudinal outcome and a single survival outcome, with data available from 5 studies.

Usage

1

Format

A list of three objects:

longitudinal

A list of long format longitudinal datasets one for each of the 5 studies included in the dataset. Each of these datasets contains the following variables:

id

long version of the id variable for the data. Identical ids between the longitudinal and the survival datasets identify the same individual

Y

a continuous longitudinal outcome

time

the longitudinal time variable

study

a long version of the study membership indicator

intercept

a long version of the intercept, always takes a value of 1

treat

a long version of the binary treatment group indicator

ltime

a duplicate of the longitudinal time variable, duplicated as part of the longitudinal data simulation process

survival

A list of survival datasets, one for each of the 5 studies included in the dataset. Each of these datasets contains the following variables:

id

the id variable for the data. Identical ids between the longitudinal and the survival datasets identify the same individual

survtime

the survival time for each individual at which they experienced the event or were censored. This is on the same scale as the longitudinal time measurements.

cens

censoring indicator for the survival data where 1 indicates an event and 0 indicates censoring

study

study membership indicator

treat

binary treatment group indicator

percentevent

A list of the percentage of events experienced in each datasets. The first element contains the percentage of events observed for the first simulated study and so on.

Details

This is a simulated dataset generated using the simjointmeta function using the following function call:

simdat<-simjointmeta(k = 5, n = rep(500, 5), sepassoc = FALSE, ntms = 5, longmeasuretimes = c(0, 1, 2, 3, 4), beta1 = c(1, 2, 3), beta2 = 3, rand_ind = 'intslope', rand_stud = 'inttreat', gamma_ind = 1, gamma_stud = 1, sigb_ind = matrix(c(1,0.5,0.5,1.5),nrow=2), sigb_stud = matrix(c(1,0.5,0.5,1.5),nrow=2), vare = 0.01, theta0 = -3, theta1 = 1, censoring = TRUE, censlam = exp(-3), truncation = TRUE, trunctime = 6)

Note that this will not give you identical data to that held in simdat due to the differences in starting seed.

See Also

simjointmeta


mesudell/joineRmeta documentation built on Jan. 24, 2020, 6:06 p.m.