Multi-dimensional simulation function for continuous-time SPM.
simdata_cont(
N = 10,
a = -0.05,
f1 = 80,
Q = 2e-08,
f = 80,
b = 5,
mu0 = 1e-05,
theta = 0.08,
ystart = 80,
tstart = 30,
tend = 105,
dt = 1,
sd0 = 1,
nobs = NULL,
gomp = TRUE,
format = "long"
)A table with simulated data.
Number of individuals.
A k by k matrix, represents the adaptive capacity of the organism
A trajectory that corresponds to the long-term average value of the stochastic process Y(t), which describes a trajectory of individual covariate (physiological variable) influenced by different factors represented by a random Wiener process W(t). This is a vector with length of k.
A matrix k by k, which is a non-negative-definite symmetric matrix, represents a sensitivity of risk function to deviation from the norm.
A vector with length of k, represents the normal (or optimal) state of physiological variable.
A diffusion coefficient, k by k matrix, characterizes a strength of the random disturbances from Wiener process W(t).
A baseline mortality.
A displacement coefficient.
A vector with length equal of k, defines starting values of covariates.
A number that defines starting time (30 by default).
A number, defines final time (105 by default).
A discrete step size between two observations. A random uniform value is then added to this step size.
a standard deviation for modelling the next covariate value.
A number of observations (lines) for individual observations.
A flag (FALSE by default). When it is set, then time-dependent exponential form of mu0 and Q are used: mu0 = mu0*exp(theta*t).
Data format: "long" (default), "short".
Yashin, A.I. et al (2007). Stochastic model for analysis of longitudinal data on aging and mortality. Mathematical Biosciences, 208(2), 538-551.<DOI:10.1016/j.mbs.2006.11.006>.
library(stpm)
dat <- simdata_cont(N=50)
head(dat)
Run the code above in your browser using DataLab