Statistics and causal inference.¶
Holland, P. W. (1986). Statistics and causal inference. Journal of the American Statistical Association, 81(396), 945-960.
Cited by¶
5 citations across 5 artifacts.
Each citation links to the sentence it supports in the citing article.
Primes¶
- Experimental Design
- Only one outcome is observed; the other is counterfactual (hypothetical), a formulation Holland (1986) crystallized as the "fundamental problem of causal inference".
This sourceCrystallizes the "fundamental problem of causal inference" — only one potential outcome is observed per unit, so causation requires comparison across units made equivalent by design.
- Only one outcome is observed; the other is counterfactual (hypothetical), a formulation Holland (1986) crystallized as the "fundamental problem of causal inference".
- Randomization
- T1 — Randomization's inferential rigor versus feasibility constraints. Randomization provides the strongest causal-inference warrant but cannot always be implemented — ethical constraints (harmful interventions cannot be randomly assigned), practical constraints (cannot randomly assign macroeconomic conditions or cultural features), scientific constraints (units must be definable, assignment must be possible)
This sourceCrystallizes the "fundamental problem of causal inference": only one potential outcome is observed per unit, so causation requires comparison across units made equivalent by design.
Supported in partVerified against the publisher's abstract
Holland's abstract backs the design-based warrant for causal conclusions, but says nothing about the ethical, practical, or scientific constraints the claim adds.
“Correlation does not imply causation, and yet causal conclusions drawn from a carefully designed experiment are often valid.”
- T1 — Randomization's inferential rigor versus feasibility constraints. Randomization provides the strongest causal-inference warrant but cannot always be implemented — ethical constraints (harmful interventions cannot be randomly assigned), practical constraints (cannot randomly assign macroeconomic conditions or cultural features), scientific constraints (units must be definable, assignment must be possible)
- Selection Bias
This sourceCrystallizes the "fundamental problem of causal inference": only one potential outcome is observed per unit, so causation requires comparison across units made equivalent by design.
Domain-specific¶
- Causal Inference
- For each unit, outcomes under mutually exclusive treatment states cannot all be observed at once
SupportedVerified against the source
- For each unit, outcomes under mutually exclusive treatment states cannot all be observed at once
Mechanisms¶
- Counterfactual Origin and Omitted-Founder Probe
- Its failure mode is that counterfactuals are unfalsifiable in principle — you can never observe the population that wasn't founded, which is the fundamental problem of causal inference
This sourceStates the fundamental problem of causal inference: factual and counterfactual responses cannot both be observed for the same unit.
- Its failure mode is that counterfactuals are unfalsifiable in principle — you can never observe the population that wasn't founded, which is the fundamental problem of causal inference
Verification¶
Does it exist? Confirmed. This work's DOI resolves to a registered record, which fixes its identity. That is all it fixes.
Does it back the claim? Read against the text for 2 of 5 citations: 1 supported, 1 supported in part. Each verdict is shown under its citation below, with what in the work backs the sentence.
Was it audited? Yes. A second, independent pass read the citation against the article text and recorded a verdict.
Support is checked per citation rather than per work — the same source can be cited soundly in one article and wrongly in another. Per-citation recording began recently, so a citation with no recorded check is a gap in the record rather than evidence it went unchecked.
See how references were verified.
Links previously used in the corpus¶
Before the registry existed this work was also linked 1 other way.
Registry ID ref:893a713e5e43 · see in the full table