popsimA: Simulation time series data for population A

In BrainCon: Inference the Partial Correlations Based on Time Series Data

Description

A dataset containing values of 10 interested variables of 20 subjects over 50 periods.

Usage

popsimA

Format

An object of class array of dimension 50 x 10 x 20.

See Also

popsimB.

Examples

## Generated by the following R codes
set.seed(1000)
n = 50
p = 10
m1 = 20; m2 = 15
precision1 = diag(rep(1, p))                  # generate precision matrix
for (i in 1 : (p - 1)){
  if (i <= 2 * p / 3) temp = -0.05
  if (i > 2 * p / 3) temp = -0.2
  precision1[i, i + 1] = temp
  precision1[i + 1, i] = temp
}
res = matrix(0, p, p)
for (i in 1 : p){
  for (j in 1 : p){
    if (abs(i - j) == 1) res[i, j] = 0.15
  }
}
precision2 = precision1 + res
Index0 = matrix(0, p, p)                     # generate covariance matrix
for (i in 1 : p){
  for (j in 1 : p){
    if (i != j & abs(i - j) <= 5) Index0[i, j] = 1
  }
}
SigmaAll1 = array(dim = c(p, p, m1))
SigmaAll2 = array(dim = c(p, p, m2))
for (sub in 1 : m1){
  RE = matrix(rnorm(p^2, 0, sqrt(2) * 0.05), p, p) * Index0
  RE1 = (RE + t(RE)) / 2
  precisionMatrixInd1 = precision1 + RE1
  SigmaInd1 = solve(precisionMatrixInd1)
  SigmaAll1[, , sub] = SigmaInd1
}
for (sub in 1 : m2){
  RE = matrix(rnorm(p^2, 0, sqrt(2) * 0.05), p, p) * Index0
  RE1 = (RE + t(RE)) / 2
  precisionMatrixInd2 = precision2 + RE1
  SigmaInd2 = solve(precisionMatrixInd2)
  SigmaAll2[, , sub] = SigmaInd2
}
rho = 0.5
Z1 = array(dim = c(n, p, m1))                # observed time series data
Z2 = array(dim = c(n, p, m2))
for (sub in 1 : m1){
  SigmaInd1 = SigmaAll1[, , sub]
  Xtemp = matrix(0, n, p)
  Epsilon = MASS::mvrnorm(n, rep(0, p), SigmaInd1)
  Xtemp[1, ] = Epsilon[1, ]
  for (i in 2 : n){
    Xtemp[i, ] = rho * Xtemp[i - 1, ] + sqrt(1 - rho^2) * Epsilon[i, ]
  }
  Z1[, , sub] = Xtemp
}
for (sub in 1 : m2){
  SigmaInd2 = SigmaAll2[, , sub]
  Xtemp = matrix(0, n, p)
  Epsilon = MASS::mvrnorm(n, rep(0, p), SigmaInd2)
  Xtemp[1, ] = Epsilon[1, ]
  for (i in 2 : n){
    Xtemp[i, ] = rho * Xtemp[i - 1, ] + sqrt(1 - rho^2) * Epsilon[i, ]
  }
  Z2[, , sub] = Xtemp
}
popsimA = Z1
popsimB = Z2

BrainCon documentation built on Sept. 30, 2021, 5:10 p.m.