Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 643

The DOI matches its Crossref record; 124 of the 124 references it cites were found in a registry or an index.

Causal Inference by using Invariant Prediction: Identification and Confidence Intervals

Open access
Peters, Jonas, Bühlmann, Peter, Meinshausen, Nicolai·2016·Journal of the Royal Statistical Society Series B: Statistical Methodology

Abstract

Summary: What is the difference between a prediction that is made with a causal model and that with a non-causal model? Suppose that we intervene on the predictor variables or change the whole environment. The predictions from a causal model will in general work as well under interventions as for observational data. In contrast, predictions from a non-causal model can potentially be very wrong if we actively intervene on variables. Here, we propose to exploit this invariance of a prediction under a causal model for causal inference: given different experimental settings (e.g. various interventions) we collect all models that do show invariance in their predictive accuracy across settings and interventions. The causal model will be a member of this set of models with high probability. This approach yields valid confidence intervals for the causal relationships in quite general scenarios. We examine the example of structural equation models in more detail and provide sufficient assumptions under which the set of causal predictors becomes identifiable. We further investigate robustness properties of our approach under model misspecification and discuss possible extensions. The empirical properties are studied for various data sets, including large-scale gene perturbation experiments.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1111/rssb.12167

Cites

124 of 124 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 124 references

Research works printed but not linked: 42

  1. Castelo, 2003, On inclusion-driven learning of Bayesian networks, J. Mach. Learn. Res., 4, 527
  2. Chickering, 2002, Optimal structure identification with greedy search, J. Mach. Learn. Res., 3, 507
  3. Cooper, 1999, Proc. 15th A. Conf. Uncertainty in Artificial Intelligence, 116
  4. Didelez, 2006, Proc. 22nd A. Conf. Uncertainty in Artifical Intelligence, 138
  5. Durot, 2013, Testing equality of functions under monotonicity constraints, J. Nonparam. Statist., 25, 939, 10.1080/10485252.2013.826356 · doi:10.1080/10485252.2013.826356
  6. Eaton, 2007, Proc. 11th Int. Conf. Artificial Intelligence and Statistics, 107
  7. Hothorn, 2010, Model-based boosting 2.0, 11, 2109
  8. Richardson, 2013, Single world intervention graphs (SWIGs): a unification of the counterfactual and graphical approaches to causality
  9. Rothenhäusler, 2015, Advances in Neural Information Processing Systems
  10. Schölkopf, 2012, Proc. 29th Int. Conf. Machine Learning, 1255
  11. Tian, 2001, Proc. 17th A. Conf. Uncertainty in Artificial Intelligence, 512
  12. Verma, 1991, Proc. 6th A. Conf. Uncertainty in Artificial Intelligence, 255
  13. Wright, 1928, The Tariff on Animal and Vegetable Oils
  14. Acid, 1996, Proc. 12th A. Conf. Uncertainty in Artificial Intelligence, 3
  15. Aldrich, 1989, Autonomy, Oxf. Econ. Pap., 41, 15, 10.1093/oxfordjournals.oep.a041889 · DOI
  16. Bollen, 1989, Structural Equations with Latent Variables, 10.1002/9781118619179 · DOI · Paper page
  17. Colombo, 2012, Learning high-dimensional directed acyclic graphs with latent and selection variables, Ann. Statist., 40, 294, 10.1214/11-AOS940 · DOI · Paper page
  18. Dawid, 2000, Causal inference without counterfactuals (with discussion), J. Am. Statist. Ass., 95, 407, 10.1080/01621459.2000.10474210 · DOI · Paper page
  19. Dawid, 2015, Statistical causality from a decision-theoretic perspective, A. Rev. Statist. Appl., 2, 273, 10.1146/annurev-statistics-010814-020105 · DOI
  20. Dawid, 2010, Identifying the consequences of dynamic treatment strategies: a decision-theoretic overview, Statist. Surv., 4, 184, 10.1214/10-SS081 · DOI
  21. Diebold, 2001, Elements of Forecasting, 254
  22. Eckardt, 2016, Point patterns occurring on complex structures in space and space-time: an alternative network approach
  23. Encyclopedia Britannica, 2014, Encyclopedia Britannica
  24. Finkenstädt, 2013, Quantifying intrinsic and extrinsic noise in gene transcription using the linear noise approximation: an application to single cell data, Ann. Appl. Statist., 7, 1960, 10.1214/13-AOAS669 · DOI
  25. van de Geer, 2014, On asymptotically optimal confidence regions and tests for high-dimensional models, Ann. Statist., 42, 1166, 10.1214/14-AOS1221 · DOI · Paper page
  26. Haavelmo, 1995, The Foundations of Econometric Analysis, 440, 10.1017/CBO9781139170116.042 · doi:10.1017/cbo9781139170116.042
  27. Hernán, 2016, Causal Inference
  28. Hoefer, 2016, The Stanford Encyclopedia of Philosophy
  29. Hora, 1967, Fiducial theory and invariant prediction, Ann. Math. Statist., 38, 795, 10.1214/aoms/1177698873 · doi:10.1214/aoms/1177698873
  30. Hoyer, 2009, Advances in Neural information Processing Systems, 689
  31. Hu, 2016, Analysis of air quality time series of Hong Kong with graphical modeling, Environmetrics, 27, 169, 10.1002/env.2386 · doi:10.1002/env.2386
  32. Kemmeren, 2014, Large-scale genetic perturbations reveal regulatory networks and an abundance of gene-specific repressors, Cell, 157, 740, 10.1016/j.cell.2014.02.054 · DOI · Paper page
  33. Luo, 2011, Bayesian hierarchical modeling for signaling pathway inference from single cell interventional data, Ann. Appl. Statist., 5, 725, 10.1214/10-AOAS425 · doi:10.1214/10-aoas425
  34. Obenchein, 1971, Multivariate procedures invariant under linear transformations, Ann. Math. Statist., 42, 1569, 10.1214/aoms/1177693155 · doi:10.1214/aoms/1177693155
  35. Peters, 2015, Causal inference using invariant prediction: identification and confidence intervals
  36. Richardson, 1996, Proc. 12th A. Conf. Uncertainty in Artificial Intelligence, 454
  37. Richardson, 2002, Ancestral graph Markov models, Ann. Statist., 30, 962, 10.1214/aos/1031689015 · DOI · Paper page
  38. Rothenhäusler, 2015, Advances in Neural Information Processing Systems, 1513
  39. Shimizu, 2006, A linear non-Gaussian acyclic model for causal discovery, J. Mach. Learn. Res., 7, 2003
  40. Spirtes, 2000, Causation, Prediction and Search
  41. Wikipedia, 2016, Wikipedia
  42. Zhu, 2004, Causal linkages among Shanghai, Shenzhen, and Hong Kong stock markets, Int. J. Theoret. Appl. Finan., 7, 135, 10.1142/S0219024904002414 · doi:10.1142/s0219024904002414

Cited by

Metadata

Authors
Peters, J., Bühlmann, P., & Meinshausen, N.
Venue
Journal of the Royal Statistical Society Series B: Statistical Methodology
Published
2016-10-11
Volume
78
Issue
5
Pages
947-1012
ISSN
  • 1369-7412
  • 1467-9868
OpenAlex
W2790376986
Cited by
643
References
124
Type
other
Language
en
Open access
green
Funders
  • European Union's seventh framework programme (FP7/2007–2013)
  • Research Executive Agency (326496)

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.