Stratifying on colliders can open biasing pathways between variables.
activate_collider_paths
activates any such pathways given a variable
or set of variables to adjust for and adds them to the tidy_dagitty
.
Arguments
- .tdy_dag
input graph, an object of class
tidy_dagitty
ordagitty
- adjust_for
a character vector, the variable(s) to adjust for.
- ...
additional arguments passed to
tidy_dagitty()
Examples
dag <- dagify(m ~ x + y, x ~ y)
collided_dag <- activate_collider_paths(dag, adjust_for = "m")
collided_dag
#> # A DAG with 3 nodes and 3 edges
#> #
#> # Paths opened by conditioning on a collider: x <-> y, x <-> y
#> #
#> # A tibble: 6 × 9
#> name x y direction to xend yend circular collider_line
#> <chr> <dbl> <dbl> <fct> <chr> <dbl> <dbl> <lgl> <lgl>
#> 1 m 0.0753 -0.401 NA NA NA NA FALSE FALSE
#> 2 x -0.928 -0.405 -> m 0.0753 -0.401 FALSE FALSE
#> 3 y -0.430 0.466 -> m 0.0753 -0.401 FALSE FALSE
#> 4 y -0.430 0.466 -> x -0.928 -0.405 FALSE FALSE
#> 5 x -0.928 -0.405 <-> y -0.430 0.466 NA TRUE
#> 6 x -0.928 -0.405 <-> y -0.430 0.466 NA TRUE