Our current identification algorithm only enables the user to automatically identify minimal adjustment sets (i.e. the smallest set of variables that blocks all back-door paths).
While this is usually preferable (less adjustments generally means a simpler statistical model), there will be some cases where a user wants to use a specific non-minimal adjusment set.
To this end, we should add a function to the CausalDAG class that obtains a list/set of all adjustment sets.
Our current identification algorithm only enables the user to automatically identify minimal adjustment sets (i.e. the smallest set of variables that blocks all back-door paths).
While this is usually preferable (less adjustments generally means a simpler statistical model), there will be some cases where a user wants to use a specific non-minimal adjusment set.
To this end, we should add a function to the CausalDAG class that obtains a list/set of all adjustment sets.