Simulates data from a graph

This is an internal simulation function for simulating data from a graph.

sim_X(B, n, sigma, alpha = rep(1, ncol(B)))

Arguments

B	a upper triangular matrix encoding a graph
n	number of observations from the graph
sigma	the common standard error
alpha	a vector of length equal to the number of parameters given by B. These alphas are multiplied to the common sigma.

Value

The sim_X function returns a matrix with data from the graph B with columns equal to the number of columns in B and rows equal to n.

Details

The sim_B function simulates a causal graph with regression coefficients. The graph must be encoded as an upper triangular matrix.

Examples

# The matrix encoding the graph with arrows:
# 1 -> 2,  1 -> 3  and  2 -> 3
(B <- matrix(c(0,0,0,1,0,0,1,1,0), ncol = 3))
#>      [,1] [,2] [,3]
#> [1,]    0    1    1
#> [2,]    0    0    1
#> [3,]    0    0    0

# simulate data
sim_X(B, 10, 1)
#>             [,1]        [,2]        [,3]
#>  [1,]  1.4042666 -0.11557251  1.85101596
#>  [2,]  0.1829870  0.22260223  1.29144096
#>  [3,] -1.6301959 -0.09758402 -0.02428655
#>  [4,] -1.1166533 -2.71256681 -3.18815300
#>  [5,]  1.4044707  2.53788974  4.26109873
#>  [6,]  0.7196067  1.76121066  2.58829278
#>  [7,]  0.1590067 -0.12270970  1.59750968
#>  [8,]  1.2461201  0.60113403  1.54382357
#>  [9,] -1.8667717 -2.31795402 -2.89937683
#> [10,] -0.1723211 -0.72949045  0.35088010