Title
Arguments
- n
TODO
- k
TODO
- ...
Arguments passed on to
model_mediator_perfectztheta_0TODO
ztheta_tTODO
ztheta_cTODO
ztheta_tcTODO
expected_degreeIf specified, the desired expected degree of the graph. Specifying
expected_degreesimply rescalesSto achieve this. Defaults toNULL. Do not specify bothexpected_degreeandexpected_densityat the same time.
Examples
set.seed(26)
mrdpg <- model_perfect(n = 100, k = 5)
graph <- sample_tidygraph(mrdpg)
graph
#> # A tbl_graph: 100 nodes and 7443 edges
#> #
#> # An undirected multigraph with 1 component
#> #
#> # Node Data: 100 × 7 (active)
#> name C1 C2 C3 C4 C5 y
#> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 1 2.75 0 0 0 0 -3.01
#> 2 2 2.64 0 0 0 0 -0.276
#> 3 3 2.60 0 0 0 0 -0.552
#> 4 4 2.59 0 0 0 0 -2.93
#> 5 5 2.47 0 0 0 0 -3.07
#> 6 6 2.34 0 0 0 0 -2.99
#> 7 7 2.12 0 0 0 0 -2.37
#> 8 8 2.10 0 0 0 0 -3.96
#> 9 9 1.94 0 0 0 0 -3.56
#> 10 10 1.68 0 0 0 0 -2.79
#> # ℹ 90 more rows
#> #
#> # Edge Data: 7,443 × 2
#> from to
#> <int> <int>
#> 1 4 7
#> 2 3 7
#> 3 2 8
#> # ℹ 7,440 more rows
m_fit <- nodelm(US(A, 5) ~ . - name - y - 1, graph = graph)
o_fit <- nodelm(y ~ . - name - 1 + US(A, 5), graph = graph)
m_fit
#>
#> Call:
#> stats::lm(formula = formula, data = data)
#>
#> Coefficients:
#> 1 2 3 4 5
#> C1 0.023484 -0.038665 0.057134 0.165749 -1.233339
#> C2 1.244640 0.069919 -0.034811 -0.018931 0.007211
#> C3 0.053376 -0.095856 1.220764 -0.076513 0.036259
#> C4 0.036883 -0.044968 0.079537 1.229718 0.150697
#> C5 0.081706 -1.243231 -0.087577 -0.032209 0.018624
#>
o_fit
#>
#> Call:
#> stats::lm(formula = formula, data = data)
#>
#> Coefficients:
#> C1 C2 C3 C4 C5 US(A, 5)1 US(A, 5)2
#> 1.4778 3.7779 5.2382 -1.0125 1.7915 -1.3699 1.5800
#> US(A, 5)3 US(A, 5)4 US(A, 5)5
#> -2.2410 0.8363 2.0560
#>