The fold changes are all based on comparison to reference level
Examples
ergm <- get_ergms(example_network, preds = "site", types = "nodemix")
#> Starting maximum pseudolikelihood estimation (MPLE):
#> Obtaining the responsible dyads.
#> Evaluating the predictor and response matrix.
#> Maximizing the pseudolikelihood.
#> Finished MPLE.
#> Evaluating log-likelihood at the estimate.
#>
#> Starting maximum pseudolikelihood estimation (MPLE):
#> Obtaining the responsible dyads.
#> Evaluating the predictor and response matrix.
#> Maximizing the pseudolikelihood.
#> Finished MPLE.
#> Evaluating log-likelihood at the estimate.
#>
get_ergm_fc(ergm[[1]])
#> # A tibble: 6 × 3
#> term theta phi
#> <chr> <dbl> <dbl>
#> 1 edges -2.11 1
#> 2 mix.site.A.B -0.725 0.513
#> 3 mix.site.B.B 1.41 3.08
#> 4 mix.site.A.C -0.837 0.462
#> 5 mix.site.B.C -0.531 0.615
#> 6 mix.site.C.C 2.01 4.40