View source: R/synthetic.dataset.R
Simulate sample trajectories of an SDE and store the results in a time.table
1 2 3 4 5 6 | synthetic.dataset(num.entities = 10, tmax = 2, steps = 100 * tmax,
process.noise.sd = 0, observation.noise.sd = 0, do.standardise = F,
initial.generator = function(i) { rnorm(3) },
det.deriv = examples.gensys.det.lorenz,
jacobian = examples.gensys.jacob.lorenz, at.times = NULL,
include.derivatives = FALSE, save.to = NULL, retries = 10)
|
num.entities |
Number of sample trajectories to generate. |
tmax |
End of the time interval to integrate the SDE over. |
steps |
Number of time steps to use in the integration. |
process.noise.sd |
Standard deviation of the brownian motion component. |
observation.noise.sd |
Standard deviation of synthetic observation noise. |
do.standardise |
Standardise the output? |
initial.generator |
Function that takes an index and generates a starting point for a sample SDE trajectory. |
det.deriv |
Function f: (m x n matrix of m states, scalar t time) -> m x n matrix of m state derivs computing the deterministic component of the dynamic given the state. |
stoch.deriv |
Function g: (1 x n matrix state, scalar t time) -> n x n matrix of noise weights, computing the stochastic coefficient of the time dynamic the state. |
jacobian |
Function J: (1 x n matrix state, scalar t time) -> n x n matrix d fi / d xj computing the jacobian of det.deriv with respect to the state variables. |
at.times |
Array of times to include in the output. Produces sample trajectories for an SDE on Ito form: dx(t) = f(x(t), t) dt + g(x(t), t) e(t) sqrt(dt) where det.deriv is f and stoch.deriv is g |
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.