Observational data
Observational data are measurements collected without the investigator assigning or controlling the conditions, treatments, or interventions being studied.
Causal Inference for Data Science
Observational data are measurements collected without assigning or controlling the conditions under which observations occur.
- How it is used
- Supports causal decisions when experiments are infeasible, while prompting analysis of confounding and assumptions.
- How deep it goes
- Explains collection, examples, confounding, stratification, DAGs, adjustment, and positivity, but defers detailed ATE computation.
- Examples
- Uses customer, sales, COVID-19, arcade-correlation, kidney-stone, and historical medical-treatment datasets.
- What you can do after
- Evaluate/understand causal claims by identifying confounders, questioning correlations, and deciding when causal inference or experiments are needed.
Read how Causal Inference for Data Science explains observational data →
Delivering Machine Learning Projects: From design to deployment
Observational data is data collected from naturally occurring conditions without deliberately assigning interventions.
- How it is used
- Frames collection motivation and observational bias as checkpoints for selecting valid inference methods and assessing production risk.
- How deep it goes
- Explains selection, missing cases, fusion, and temporal distortion, but stops short of statistical correction procedures.
- Examples
- Uses a selective butterfly collection and retail snapshots taken on different weekdays to illustrate representation and temporal bias.
- What you can do after
- Evaluate inference and modeling risks by documenting collection motivation, selection effects, fusion choices, and hidden time ranges.
Causal AI
Observational data are measurements collected without the investigator assigning the treatment or intervention being studied.
- How it is used
- Supports causal questions when randomized experiments are unavailable, while distinguishing observed associations from intervention effects.
- How deep it goes
- Defines passive measurement, demonstrates group statistics, and places it in the causal hierarchy; stops short of treating association as causation.
- Examples
- Uses logged game-player records, grouped purchase summaries, a mean-difference test, and a pandas workflow.
- What you can do after
- Evaluate whether passive observations can support causal claims and recognize when identification assumptions or interventions are required.
Related concepts
- causal hierarchy theorempart of · The causal hierarchy theorem states that observational, interventional, and counterfactual information are generally distinct levels that cannot be inferred from lower-level information without assumptions corresponding to the higher level.
- experimentationcontrasts with · Experimentation is the deliberate testing of an idea, intervention, or alternative by observing outcomes to gather evidence or compare effects.
- causal inferenceused by · Causal inference is the process of determining or estimating how causes, exposures, or interventions affect outcomes, using data and assumptions about causal relationships.
- causal adjustmentused by · Causal adjustment estimates a causal effect by conditioning on variables that block noncausal pathways and averaging over their target-population distribution.
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.