External Validity: From Do-Calculus to Transportability Across Populations

@article{Pearl2015ExternalVF,
  title={External Validity: From Do-Calculus to Transportability Across Populations},
  author={Judea Pearl and Elias Bareinboim},
  journal={ArXiv},
  year={2015},
  volume={abs/1503.01603}
}
The generalizability of empirical findings to new environments, settings or populations, often called "external validity," is essential in most scientific explorations. This paper treats a particular problem of generalizability, called "transportability," defined as a license to transfer causal effects learned in experimental studies to a new population, in which only observational studies can be conducted. We introduce a formal representation called "selection diagrams" for expressing… Expand
Generalizability of causal and statistical relations
The problem of generalizability of empirical findings (experimental and observational) to new environments, settings, and populations is one of the central problems in causal inference. ExperimentsExpand
Towards causally interpretable meta-analysis: transporting inferences from multiple studies to a target population
We take steps towards causally interpretable meta-analysis by describing methods for transporting causal inferences from a collection of randomized trials to a new target population,Expand
Toward Causally Interpretable Meta-analysis: Transporting Inferences from Multiple Randomized Trials to a New Target Population.
We take steps toward causally interpretable meta-analysis by describing methods for transporting causal inferences from a collection of randomized trials to a new target population, one trial at aExpand
Generalizing Study Results: A Potential Outcomes Perspective.
TLDR
This work discusses how a version of direct standardization (the g-formula, adjustment formula, or transport formula) or inverse probability weighting can be used to generalize a causal effect from a study sample to a well-defined target population, and demonstrates their application in an illustrative example. Expand
Generalizing experimental results by leveraging knowledge of mechanisms
TLDR
This work uses structural causal models and a refined version of selection diagrams to represent knowledge of local mechanisms that produce the outcome of interest and decides whether it entails the invariance of probabilities of causation across populations, which then enables generalization. Expand
A Unified Approach to Generalized Causal Inference
Randomized controlled trials and natural experiments have been criticized for their lack of generalizability (external validity), questioning their usefulness to social science and policy. Here IExpand
A Unified Approach to Generalized Causal Inference
Randomized controlled trials and natural experiments have been criticized for their lack of generalizability (external validity), questioning their usefulness to social science and policy. Here IExpand
On the utility of causal diagrams in modeling attrition: a practical example.
TLDR
It is shown that more natural solutions to attrition problems are obtained when viewed as missing-data problems encoded in causal diagrams, and in fact longer and more complicated than the standard, three-step derivation facilitated by traditional causal diagrams. Expand
Target Validity and the Hierarchy of Study Designs.
TLDR
It is shown that even perfect internal validity does not ensure that a causal effect will be unbiased in a specific target population, and a joint measure of the validity of an effect estimate with respect to a specific population of interest may be more useful. Expand
Comment
Stabilizing estimates derived from focused, internally valid studies by “docking” to relatively coarse, external information is increasingly possible and important, and we applaud Chatterjee, Chen,Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 111 REFERENCES
Transportability across studies: A formal approach
TLDR
It is demonstrated how transportability analysis can guide the transfer of knowledge among non-experimental studies to minimize re-measurement cost and improve prediction power. Expand
A General Algorithm for Deciding Transportability of Experimental Results
TLDR
This article establishes a necessary and sufficient condition for deciding when causal effects in the target population are estimable from both the statistical information available and the causal information transferred from the experiments, and provides a complete algorithm for computing the transport formula. Expand
Transportability of Causal Effects: Completeness Results
TLDR
This paper establishes a necessary and sufficient condition for deciding when causal effects in the target domain are estimable from both the statistical information available and the causal information transferred from the experiments. Expand
Causal Transportability with Limited Experiments
TLDR
This paper establishes a necessary and sufficient condition for causal effects in the target domain to be estimable from both the non-experimental information available and the limited experimental information transferred from the source. Expand
Meta-Transportability of Causal Effects: A Formal Approach
TLDR
This paper provides a complete algorithm for computing the transport formula, that is, a way of fusing observational and experimental information to synthesize an unbiased estimate of the desired eects in the target domain. Expand
Causation, Prediction, and Search, 2nd Edition
What assumptions and methods allow us to turn observations into causal knowledge, and how can even incomplete causal knowledge be used in planning and prediction to influence and control ourExpand
Compound Treatments and Transportability of Causal Inference
TLDR
The causal effect of compound treatments and their identifiability conditions are described and how such issues of “transportability” are related to the consistency condition in causal inference are discussed. Expand
Causal inference in statistics: An overview
This review presents empiricalresearcherswith recent advances in causal inference, and stresses the paradigmatic shifts that must be un- dertaken in moving from traditionalstatistical analysis toExpand
Pearl's D-Separation: One More Step Into Causal Thinking
It is frequently claimed that experiments can attest to causal assertions, whereas cross-sectional survey research cannot underwrite similar causal claims. Some logical deficiencies with derivingExpand
Estimating causal effects of treatments in randomized and nonrandomized studies.
A discussion of matching, randomization, random sampling, and other methods of controlling extraneous variation is presented. The objective is to specify the benefits of randomization in estimatingExpand
...
1
2
3
4
5
...