Synthese

, Volume 121, Issue 1–2, pp 29–54 | Cite as

Are There Algorithms That Discover Causal Structure?

  • David Freedman
  • Paul Humphreys
Article

Abstract

There have been many efforts to infer causation from association byusing statistical models. Algorithms for automating this processare a more recent innovation. In Humphreys and Freedman[(1996) British Journal for the Philosophy of Science47, 113–123] we showed that one such approach, by Spirtes et al., was fatally flawed. Here we put our arguments in a broader context and reply to Korb and Wallace [(1997) British Journal for thePhilosophy of Science48, 543–553] and to Spirtes et al.[(1997) British Journal for the Philosophy of Science48, 555–568]. Their arguments leave our position unchanged: claims to have developed a rigorous engine for inferring causation from association are premature at best, the theorems have no implications for samples of any realistic size, and the examples used to illustrate the algorithms are indicative of failure rather than success. The gap between association and causation has yet to be bridged.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

REFERENCES

  1. Abbott, A.: 1997, 'Of Time and Space: The Contemporary Relevance of the Chicago School', Social Forces 75, 1149–1182.Google Scholar
  2. Blau, P. M. and O. D. Duncan: 1967, The American Occupational Structure. John Wiley, New York.Google Scholar
  3. Carlin, J. B., T. P. Speed and H. T. Kiiveri: 1984, 'Recursive Causal Models', Journal of the Australian Mathematical Society Series A, 36, 30–52Google Scholar
  4. Cornfield, J., W. Haenszel, E. C. Hammond, A. M. Lilienfeld, M. B. Shimkin and E. L. Wynder: 1959, 'Smoking and Lung Cancer: Recent Evidence and a Discussion of Some Questions', Journal of the National Cancer Institute 22, 173–203.Google Scholar
  5. Daggett, R. and D. Freedman: 1985, 'Econometrics and the Law: A Case Study in the Proof of Antitrust Damages', in L. LeCam and R. Olshen (eds.), Proceedings of the Berkeley Conference in Honor of Jerzy Neyman and Jack Kiefer, Vol. I. Wadsworth, Belmont, CA, pp. 126–175.Google Scholar
  6. Darroch, J. N., S. L. Lauritzen and T. P. Speed: 1980, 'Markov Fields and Log-Linear Interaction Models for Contingency Tables', Annals of Statistics 8, 522–539.Google Scholar
  7. Freedman, D.: 1985, 'Statistics and the Scientific Method', in W. M. Mason and S. E. Fienberg (eds.), Cohort Analysis in Social Research: Beyond the Identification Problem. Springer-Verlag, New York, pp. 343–390 (with discussion).Google Scholar
  8. Freedman, D.: 1987, 'As Others See Us: A Case Study in Path Analysis', Journal of Educational Statistics 12(2) (with discussion).Google Scholar
  9. Freedman, D.: 1991, 'Statistical Models and Shoe Leather', in P. Marsden (ed.), Sociological Methodology 1991. American Sociological Association, Washington, DC (with discussion).Google Scholar
  10. Freedman, D.: 1995, 'Some Issues in the Foundation of Statistics', Foundations of Science 1, 19–83 (with discussion). Reprinted in B. van Fraasen (ed.), Some Issues in the Foundation of Statistics. Kluwer, Dordrecht.Google Scholar
  11. Freedman, D.: 1997, 'From Association to Causation via Regression', in V. McKim and S. Turner (eds.), Causality in Crisis? University of Notre Dame Press, pp. 113–182 (with discussion).Google Scholar
  12. Freedman, D., T. Rothenberg and R. Sutch: 1983, 'On Energy Policy Models', Journal of Business and Economic Statistics 1, 24–36 (with discussion).Google Scholar
  13. Geiger, D., T. Verma and J. Pearl: 1990, 'Identifying Independence in Bayesian Networks', Networks 2, 507–534.Google Scholar
  14. Glymour, C.: 1997, 'A Review of Recent Work on the Foundations of Causal Inference', in V. McKim and S. Turner (eds.), Causality in Crisis? University of Notre Dame Press, pp. 201–248.Google Scholar
  15. Goldthorpe, J. H.: 1998, 'Causation, Statistics and Sociology', twenty-ninth Geary Lecture, Nuffield College, Oxford. Published by the Economic and Social Research Institute, Dublin, Ireland.Google Scholar
  16. Greenland, S., J. Pearl and J. Robins: 1999, 'Causal Diagrams for Epidemiologic Research', Epidemiology 10, 37–48.Google Scholar
  17. Hodges, J. L., Jr. and E. Lehmann: 1964, Basic Concepts of Probability and Statistics. Holden-Day, San Francisco.Google Scholar
  18. Holland, P.: 1986, 'Statistics and Causal Inference', Journal of the American Statistical Association 8, 945–960.Google Scholar
  19. Holland, P.: 1988, 'Causal Inference, Path Analysis, and Recursive Structural Equations Models', in C. Clogg (ed.), Sociological Methodology 1988. American Sociological Association, Washington, DC, pp. 449–484.Google Scholar
  20. Humphreys, P.: 1989, The Chances of Explanation: Causal Explanation in the Social, Medical, and Physical Sciences. Princeton University Press, Princeton, NJ.Google Scholar
  21. Humphreys, P.: 1997, 'A Critical Appraisal of Causal Discovery Algorithms', in V. McKim and S. Turner (eds.), Causality in Crisis? University of Notre Dame Press, pp. 249–263.Google Scholar
  22. Humphreys, P. and D. Freedman: 1996, 'The Grand Leap', British Journal for the Philosophy of Science 47, 113–123.Google Scholar
  23. International Agency for Research on Cancer: 1986, Tobacco Smoking. Monographs on the Evaluation of the Carcinogenic Risk of Chemicals to Humans, Vol. 38. IARC, Lyon, France.Google Scholar
  24. Keynes, J. M.: 1939, 'Professor Tinbergen's Method', The Economic Journal 49, 558–570.Google Scholar
  25. Keynes, J. M.: 1940, 'Comment on Tinbergen's Response', The Economic Journal 50, 154–156.Google Scholar
  26. Kiiveri, H. T. and T. P. Speed: 1982, 'Structural Analysis of Multivariate Data: A Review', in S. Leinhardt (ed.), Sociological Methodology 1982. Jossey Bass, San Francisco.Google Scholar
  27. Kiiveri, H. T. and T. P. Speed: 1986, 'Gaussian Markov Distributions Over Finite Graphs', Annals of Statistics 14, 138–150.Google Scholar
  28. Korb, K. B. and C. S. Wallace: 1997, 'In Search of the Philosopher's Stone: Remarks on Humphreys and Freedman's Critique of Causal Discovery', British Journal for the Philosophy of Science 48, 543–553.Google Scholar
  29. Lauritzen, S. L.: 1996, Graphical Models. Oxford University Press, New York.Google Scholar
  30. Lauritzen, S. L., A. P. Dawid, B. N. Larsen and H.-G. Leimer: 1990, 'Independence Properties of Directed Markov Fields', Networks 20, 491–505.Google Scholar
  31. Liu, T. C.: 1960, 'Under-identification, Structural Estimation, and Forecasting', Econometrica 28, 855–865.Google Scholar
  32. Lucas, R. E. Jr.: 1976, 'Econometric Policy Evaluation: A Critique', in K. Brunner and A. Meltzer (eds.), The Phillips Curve and Labor Markets, Vol. 1 of the Carnegie-Rochester Conferences on Public Policy, supplementary series to the Journal of Monetary Economcs. North-Holland, Amsterdam, pp. 19–64(with discussion).Google Scholar
  33. Manski, C. F.: 1993, 'Identification Problems in the Social Sciences'. In P. V. Marsden (ed.), Sociological Methodology 1993. Basil Blackwell, Oxford, pp. 1–56.Google Scholar
  34. Meehl, P.: 1978, 'Theoretical Risks and Tabular Asterisks: Sir Karl, Sir Ronald, and the Slow Progress of Soft Psychology', Journal of Consulting and Clinical Psychology 46, 806–834.Google Scholar
  35. Neyman, J.: 1923, 'Sur les applications de la théorie des probabilités aux experiences agricoles: essai des principes', Roczniki Nauk Rolniczki 10, 1–51, in Polish; English translation by D. Dabrowska and T. Speed: 1991, Statistical Science 5, 463–480.Google Scholar
  36. Pearl, J.: 1986, 'Fusion Propagation and Structuring in Belief Networks', Artificial Intelligence 29, 241–288.Google Scholar
  37. Pearl, J.: 1988, Probabilistic Reasoning in Intelligent Systems. Morgan Kaufmann, San Mateo, CA.Google Scholar
  38. Pearl, J.: 1995, 'Causal Diagrams for Empirical Research', Biometrika 82, 669–710(with discussion).Google Scholar
  39. Pearl, J. and T. Verma: 1991, 'A Theory of Inferred Causation', in J. A. Allen, R. Fikes and E. Sandewall (eds.), Principles of Knowledge Representation and Reasoning: Proceedings of the Second International Conference. Morgan Kaufmann, San Mateo, CA, pp. 441–452.Google Scholar
  40. Rebane, G. and J. Pearl: 1987, 'The Recovery of Causal Poly-trees from Statistical Data', Proceedings, AAAI Workshop on Uncertainty in AI, Seattle, WA, pp. 222–228. Also in L. N. Kanal, T. S. Levitt and J. F. Lemmer (eds.): 1989, Uncertainty in Artificial Intelligence 3. Elsevier Science Publishers, Amsterdam, pp. 175–182.Google Scholar
  41. Rindfuss, R. R., L. Bumpass and C. St. John: 1980, 'Education and Fertility: Implications for the Roles Women Occupy', American Sociological Review 45, 431–447.Google Scholar
  42. Robins, J. M.: 1986, 'A New Approach to Causal Inference in Mortality Studies with a Sustained Exposure Period-Application to Control of the Healthy Worker Survivor Effect', Mathematical Modelling 7, 1393–1512.Google Scholar
  43. Robins, J. M.: 1987a, 'A Graphical Approach to the Identification and Estimation of Causal Parameters in Mortality Studies with Sustained Exposure Periods', Journal of Chronic Diseases 40, Supplement 2, 139S-161S.Google Scholar
  44. Robins, J. M.: 1987b, 'Addendum to 'A New Approach to Causal Inference in Mortality Studies with a Sustained Exposure Period-Application to Control of the Healthy Worker Survivor Effect'', Comp. Math. Applic. 14, 923–945.Google Scholar
  45. Robins, J. M.: 1993, 'Analytic Methods for Estimating HIV Treatment and Cofactor Effects', in D. G. Ostrow and R. Kessler (eds.), Methodological Issues of AIDS Mental Health Research. Plenum, NewYork.Google Scholar
  46. Robins, J. M. and L. Wasserman: 1999, 'On the Impossibility of Inferring Causation from Association without Background Knowledge', in C. Glymour and G. F. Cooper, (eds.), Computation, Causation and Discovery. AAAI Press, Menlo Park, CA.Google Scholar
  47. Rubin, D.: 1974, 'Estimating Causal Effects of Treatments in Randomized and Nonrandomized Studies', Journal of Educational Psychology 66, 688–701.Google Scholar
  48. Scheffé, H.: 1936, 'Models in the Analysis of Variance', Annals of Mathematical Statistics 27.Google Scholar
  49. Scheines, R.: 1997, 'An Introduction to Causal Inference', in V. McKim and S. Turner (eds.), Causality in Crisis? University of Notre Dame Press, pp. 185–199.Google Scholar
  50. Spirtes, P. and R. Scheines: 1997, 'Reply to Freedman', in V. McKim and S. Turner (eds.), Causality in Crisis? University of Notre Dame Press, pp. 163–176.Google Scholar
  51. Spirtes, P., R. Scheines, C. Glymour and C. Meek: 1993, TETRAD II. Documentation for Ver s i on 2. 2. Technical Report, Department of Philosophy, Carnegie Mellon University, Pittsburgh, PA.Google Scholar
  52. Spirtes, P., C. Glymour and R. Scheines: 1993, Causation, Prediction, and Search. Springer Lecture Notes in Statistics, No. 81. Springer-Verlag, New York.Google Scholar
  53. Spirtes, P., C. Glymour and R. Scheines: 1997, 'Reply to Humphreys and Freedman's Review of Causation, Prediction, and Search', British Journal for the Philosophy of Science 48, 555–568.Google Scholar
  54. Timberlake, M. and K. Williams: 1984, 'Dependence, Political Exclusion and Government Repression: Some Cross National Evidence', American Sociological Review 49, 141–146.Google Scholar
  55. Tinbergen, J.: 1940, 'Reply to Keynes', The Economic Journal 50, 141–154.Google Scholar
  56. US Department of Health and Human Services: 1990, The Health Benefits of Smoking Cessation, a Report of the Surgeon General, Washington, DC.Google Scholar
  57. Woodward, J.: 1997, 'Causal Models, Probabilities, and Invariance', in V. McKim and S. Turner (eds.), Causality in Crisis? University of Notre Dame Press, pp. 265–315.Google Scholar
  58. Wright, S.: 1921, 'Correlation and Causation', Journal of Agricultural Research 20, 557–585.Google Scholar

Copyright information

© Kluwer Academic Publishers 1999

Authors and Affiliations

  • David Freedman
    • 1
  • Paul Humphreys
    • 2
  1. 1.Department of StatisticsUniversity of California, BerkeleyBerkeleyUSA
  2. 2.Department of PhilosophyUniversity of VirginiaCharlottesvilleUSA

Personalised recommendations