Graphical identification in declared acyclic directed mixed graphs (ADMGs). Directed edges are causal assumptions; bidirected edges represent latent common causes. This is not a causal interpretation inferred from source.
identify implements Shpitser and Pearl's ID/IDC algorithms (2006).
It returns an observational functional or a nonidentification witness.
Identification assumes the graph, its latent-variable interpretation and
the positivity required by the functional. It does not fit mechanisms.
Expressions are data and can be evaluated on finite probability tables.
Graphical identification in declared acyclic directed mixed graphs (ADMGs). Directed edges are causal assumptions; bidirected edges represent latent common causes. This is not a causal interpretation inferred from source. `identify` implements Shpitser and Pearl's ID/IDC algorithms (2006). It returns an observational functional or a nonidentification witness. Identification assumes the graph, its latent-variable interpretation and the positivity required by the functional. It does not fit mechanisms. Expressions are data and can be evaluated on finite probability tables.
(ancestors g nodes)Directed ancestors, including nodes themselves.
Directed ancestors, including `nodes` themselves.
(districts g)Maximal bidirected-connected components, including isolated nodes.
Maximal bidirected-connected components, including isolated nodes.
(evaluate expression domains probability assignment)Evaluate an identified expression on a finite probability oracle.
probability takes maps of event values and conditioning values.
domains gives finite supports for summed variables. Undefined ratios
(including positivity failures) are refused. Continuous integrals need
a different evaluator; symbolic identification itself is not discrete.
Evaluate an identified expression on a finite probability oracle. `probability` takes maps of event values and conditioning values. `domains` gives finite supports for summed variables. Undefined ratios (including positivity failures) are refused. Continuous integrals need a different evaluator; symbolic identification itself is not discrete.
(graph {:keys [nodes directed bidirected]})Declare {:nodes #{…} :directed [[cause effect] …] :bidirected [[a b] …]}. Nodes can be inferred from edges, but isolated nodes must be supplied.
Declare {:nodes #{…} :directed [[cause effect] …] :bidirected [[a b] …]}.
Nodes can be inferred from edges, but isolated nodes must be supplied.(identify g {:keys [outcomes treatments given]})Identify P(outcomes | do(treatments), given) from P(V) in an ADMG. Returns :identified with :expression, or :not-identified with a witness. Scope is nonparametric observational identification in a semi-Markovian acyclic model; it is not an algebraic parameter-identifiability verdict.
Identify P(outcomes | do(treatments), given) from P(V) in an ADMG. Returns :identified with :expression, or :not-identified with a witness. Scope is nonparametric observational identification in a semi-Markovian acyclic model; it is not an algebraic parameter-identifiability verdict.
(m-separated? g left right conditioned)m-separation by latent expansion and ancestral moralization.
m-separation by latent expansion and ancestral moralization.
cljdoc builds & hosts documentation for Clojure/Script libraries
| Ctrl+k | Jump to recent docs |
| ← | Move to previous article |
| → | Move to next article |
| Ctrl+/ | Jump to the search field |