Causal graphical model
A causal graphical model is a probabilistic or structural model whose graph represents causal relationships and whose mechanisms support reasoning about interventions.
Causal AI
A causal generative model is a generative probabilistic model whose structure represents causal mechanisms and supports intervention-based generation of distributions.
- How it is used
- Uses a causal DAG to scaffold a probabilistic model of the data-generating process for causal inference and prediction across settings.
- How deep it goes
- Works through graph construction, parent-conditioned factorization, parameter learning, and refutation; defers more sophisticated neural-network models.
- Examples
- Uses commuting choices, rock throwing, and digit handwriting to make causal assumptions concrete.
- What you can do after
- Build it from scratch with pgmpy, learn its parameters, and diagnose conflicting conditional-independence claims through refutation.
Causal Inference for Data Science
A causal graphical model represents causal relationships among variables with a graph together with a probabilistic or structural model.
- How it is used
- Frames intervention questions by encoding hypothesized direct effects and causal pathways among variables.
- How deep it goes
- Explains graph construction through arrow assumptions, confounders, mediators, direction ambiguity, and cyclic-graph limitations.
- Examples
- Uses Topic, Platform, Pageviews, Seasonality, and Popularity to illustrate confounding and mediation.
- What you can do after
- Evaluate causal assumptions by drawing arrows, identifying confounders and mediators, and recognizing when data cannot determine direction.
Read how Causal Inference for Data Science explains causal graphical model →
Related concepts
- structural causal modelincludes · A structural causal model represents causal relationships among variables through equations that determine each variable from other variables and exogenous factors.
- causal discoveryproduced by · Causal discovery is the process of inferring causal relationships or a causal graph from data under assumptions about the data-generating process.
- d-separationproduces · D-separation is a graphical criterion for determining whether a conditioning set blocks all relevant paths between variables in a graph, implying conditional independence under the graph’s assumptions.
- directed acyclic graphkind of · A directed acyclic graph is a graph with directed edges and no directed cycles.
- conditional independenceuses · Two variables are conditionally independent given specified information when their conditional joint distribution factors into the product of their conditional distributions.
- parallel world graphincludes · A parallel world graph is a graph representation that places variables from multiple counterfactual worlds together without necessarily permitting the same separation relations as a counterfactual graph.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.