simulate_mvt_poisson: Simulate multivariate Poisson data with a given correlation...

In andreamrau/rpl: Randomized pairwise likelihood method for complex statistical inferences

Simulate multivariate Poisson data with a given correlation matrix structure using Gaussian copulas

Description

Simulate multivariate Poisson data with a given correlation matrix structure using Gaussian copulas

Usage

simulate_mvt_poisson(
  n = 1000,
  d = 4,
  param,
  offsets = NULL,
  type = "unstructured",
  block_indices = NULL
)

Arguments

n	Number of observations to simulate
d	Dimension of variables to simulate
param	Named list ("margins", "disp") of parameters to be used for simulation. Parameters should first include marginal parameters, then vectorized correlation parameters in lexicographical order. The size of the disp vector depends on the type of correlation matrix structure to be simulated.
offsets	If needed, a matrix of offsets (optional)
type	Type of correlation matrix structure to be simulated: unstructured ((d^2 - d)/2 correlation parameters), exchangeable (1 correlation parameter), one-factor (d theta parameters, where rho_ij = theta_i * theta_j), block_exchangeable (for b blocks, (b^2 - b)/2 correlation parameters).
block_indices	For type="block_exchangeable", list containing the indices of variables belonging to each of the b blocks.

Value

data	Matrix of simulated data
param	True parameter values used to simulate data

andreamrau/rpl documentation built on April 26, 2023, 3:57 p.m.