sim_rrsm: Simulate large spatial dataset

In jelsema/RRSM: Methods for reduced rank spatial models

Description

Simulates a large spatial dataset according to a Spatial Random Effects model: Y = Xβ + Sη + ε

Usage

sim_rrsm(X, S, beta = NULL, V = NULL, ssq = 0.001, theta = NULL,
  coords = NULL, knots = NULL, dist = "mvrnorm", seed = NULL, ...)

Arguments

X	the design matrix for the large-scale variation (fixed effects).
S	the matrix of basis functions (design matrix for the random effect).
beta	the large-scale variation vector (fixed-effects slopes).
V	the covariance matrix of the reduced rank process.
ssq	the residual variance.
theta	the spatial dependence parameter, for if V needs to be calculated.
coords	the observed locations, for if S needs to be calculated.
knots	the knot locations, for if S needs to be calculated.
dist	the distribution to use for simulating data. Currently only "mvrnorm" is supported.
seed	optional means to control the RNG seed.
...	space for additional arguments.

Value

A vector containing the simulated values.

Note

Several arguments, including S, V, and ssq may be left empty, if locations and knots are provided to calculate them.

jelsema/RRSM documentation built on May 19, 2019, 4:02 a.m.