Computational Statistics

, 21:151 | Cite as

Constraint-based inference algorithms for structural models with latent confounders— empirical application and simulations

  • Dirk Temme
Article
  • 80 Downloads

Summary

Graphical methods for the discovery of structural models from observational data provide interesting tools for applied researchers. A problem often faced in empirical studies is the presence of latent confounders which produce associations between the observed variables. Although causal inference algorithms exist which can cope with latent confounders, empirical applications assessing the performance of such algorithms are largely lacking. In this study, we apply the constraint based Fast Causal Inference algorithm implemented in the software program TETRAD on a data set containing strategy and performance information about 608 business units. In contrast to the informative and reasonable results for the impirical data, simulation findings reveal problems in recovering some of the structural relations.

Key words

Structural equation modelling Graphical models Constrait-based inference algorithms 
This is a preview of subscription content, log in to check access.

References

  1. Acid, S. & de Campos, L. (2003), “Searching for Bayesian Network Structures in the Space of Restricted Acyclic Partially Directed Graphs”, Journal of Artificial Intelligence Research 18, 445–490.MATHMathSciNetGoogle Scholar
  2. Ailawadi, K., Farris, P. & Parry, M. (1999), “Market Share and ROI: Observing the Effect of Unobserved Variables”, International Journal of Research in Marketing 16, 17–33.CrossRefGoogle Scholar
  3. Annacker, D. & Hildebrandt, L. (2004), “Unobservable Effects in Structural Models of Business Performance”, Journal of Business Research 57, 507–517.CrossRefGoogle Scholar
  4. Bagozzi, R. & Baumgartner, H. (1994), “The Evaluation of Structural Equation Models and Hypothesis Testing”, in Principles of Marketing Research, R. Bagozzi, ed., Basil Blackwell, Cambridge, 386–422.Google Scholar
  5. Bollen, K. (1989), Structural Equations With Latent Variables, Wiley, New York.MATHGoogle Scholar
  6. Boulding, W. & Staelin, R. (1993), “A Look on the Cost Side: Market Share and the Competitive Environment”, Management Science 12, 144–166.Google Scholar
  7. Browne, M. & Cudeck, R. (1993), “Alternative Ways of Assessing Model Fit”, in K. Bollen & J. Long, eds., Testing Structural Equation Models, Sage, Newbury Park, 136–162.Google Scholar
  8. Buzzell, R. & Gale, B. (1987), The PIMS Principles, Free Press, New YorkGoogle Scholar
  9. Cliff, N. (1983), ‘Some Cautions Concerning the Application of Causal Modeling Methods”, Multivariate Behavioral Research 18, 115–126.CrossRefGoogle Scholar
  10. Cooper, G. (1999), “An Overview of the Representation and Discovery of Causal Relationships Using Bayesian Networks’, in Computation, Causation and Discovery, G. Glymour & G. Cooper, eds., MIT Press, Cambridge, 3–62.Google Scholar
  11. Cooper, G. & Herskovits, E. (1991), “A Bayesian Method for Constructing Bayesian Belief Networks from Databases”, in Proceedings of the Conference on Uncertainty in Artificial Intelligence, Morgan-Kaufman, San Francisco, 86–94.Google Scholar
  12. Dawid, A. (1979), “Conditional Independence in Statistical Theory”, Journal of the Royal Statistical Society 41, B, 1–31.MATHMathSciNetGoogle Scholar
  13. Elidan, G. & Friedman, N. (2003), “The Information Bottleneck EM algorithm”, in Proceedings of the Ninetieth Conference on Uncertainty in Artificial Intelligence, Morgan Kaufmann, San Francisco, 200–208.Google Scholar
  14. Elidan, G., Lotner, N., Friedman, N. & Koller, D. (2001), “Discovering Hidden Variables: A Structure-Based Approach”, in Advances in Neural Information Processing Systems 13 (NIPS 2000), T. Leen, T. Diettrich & V. Tresp, eds., MIT Press, Cambridge, 479–485.Google Scholar
  15. Freedman, D. (1987), “As Others See Us: A Case Study in Path Analysis”, Journal of Educational Statistics 12, 101–128.CrossRefGoogle Scholar
  16. Griliches, Z. (1974), “Errors in Variables and Other Unobservables”, Econometrica 42, 971–998.MATHMathSciNetCrossRefGoogle Scholar
  17. Harwood, S. & Scheines, R. (2002), “Genetic Algorithm Search Over Causal Models”, Technical Report CMU-Phil-131, Carnegie Mellon University, Pittsburgh.Google Scholar
  18. Hildebrandt, L. & Buzzell, R. (1991), “Product Quality, Market Share, and Profitability: A Causal Modelling Approach”, Working Paper 91-045, Harvard Business School, Cambridge.Google Scholar
  19. Hildebrandt, L & Temme, D. (2004), “The Model by Phillips, Chang and Buzzell Revisited—the Effects of Unobservable Variables”, in The Profit Impact of Marketing Strategy: Retrospect and Prospects, P.W. Farris & M.J. Moore, eds., Cambridge University Press, Cambridge, 153–187.Google Scholar
  20. Heckerman, D., Meek, C. & Cooper, G. (1999), “A Bayesian Approach to Causal Discovery”, in Computation, Causation and Discovery, G. Glymour & G. Cooper, eds., MIT Press, Cambridge, 141–165.Google Scholar
  21. Hu, L. & Bentler, P. (1999), “Cutoff Criteria for Fit Indexes in Covariance Structure Analysis: Conventional Criteria Versus New Alternatives”, Structural Equation Modeling 6, 1–55.CrossRefGoogle Scholar
  22. Hu, L. & Bentler, P. (1998), “Fit Indices in Covariance Structure Modeling: Sensitivity to Underparameterized Model Misspecification”, Psychological Methods 3, 424–453.CrossRefGoogle Scholar
  23. Jacobson, R. (1990), “Unobservable Effects and Business Performance”, Marketing Science 9, 74–85.CrossRefGoogle Scholar
  24. Jöreskog, K & Sörbom, D. (1996), LISREL 8: User's Reference Guide, Scientific Software, Chicago.Google Scholar
  25. Lacruz, B., Lasala, P. & Lekuona, A., (2001), Selecting Dynamic Graphical Models with Hidden Variables from Data, Computational Statistics, 16, 173–194.MATHMathSciNetCrossRefGoogle Scholar
  26. Laurent, G. (2000), “Improving the External Validity of Marketing Models: A Plea for More Qualitative Input”, International Journal of Research in Marketing 17, 177–182.CrossRefGoogle Scholar
  27. Lauritzen, S., Dawid, P., Larsen, B. & Leimer, H. (1990), “Independence Properties of Directed Markov Fields”, Networks 20, 491–505.MATHMathSciNetGoogle Scholar
  28. Lee, S. & Hershberger, S. (1990), “A simple rule for generating equivalent models in covariance structure modelling”, Multivariate Behavioral Research 25, 313–334.CrossRefGoogle Scholar
  29. MacCallum, R., Roznowski, M. & Necowitz, L. (1992), “Model Modification in Covariance Structure Analysis: The Problem of Capitalization On Chance”, Psychological Bulletin 111, 490–504.CrossRefGoogle Scholar
  30. Nachman, I., Elidan, G. & Friedman, N. (2004), “‘Ideal Parent’ Structure Learning for Continuous Variable Networks”, in Proceedings of the Twentieth Conference on Uncertainty in Artificial Intelligence, Morgan Kaufmann, San Francisco.Google Scholar
  31. Pearl, J. (1988), Probabilistic Reasoning in Intelligent Systems, Morgan-Kaufman, San Mateo.MATHGoogle Scholar
  32. Pearl, J. (1988), “Graphs, Causality, and Structural Equation Models”, Sociological Methods and Research 27, 226–284.Google Scholar
  33. Pearl, J. (2000), Causality: Models, Reasoning, and Inference, Cambridge University Press, Cambridge.MATHGoogle Scholar
  34. Phillips, L., Chang, D. & Buzzell, R. (1983), “Product Quality Cost Position, and Business Performance: A Test of Some Key Hypotheses” Journal of Marketing 47 (Spring), 26–43.CrossRefGoogle Scholar
  35. Richardson, T. (1996), “A Discovery Algorithm for Directed Cyclic Graphs”, in Proceedings of the 12th Conference on Uncertainty in Artificial Intelligence, Morgan Kaufmann, San Francisco, 454–461.Google Scholar
  36. Scheines, R., Spirtes, P., Glymour, C. & Meek, C. (1994), TETRAD II: Tools for Causal Modeling, USer's Manual, Lawrence Erlbaum, Hillsdale.Google Scholar
  37. Scheines, R., Spirtes, P., Glymour, C., Meek, C. & Richardson, T. (1998), “The TETRAD Project: Constraint Based Aids to Causal Model Specification”, Multivariate Behavioral Research 33, 65–117.CrossRefGoogle Scholar
  38. Scheines, R., Spirtes, P., Glymour, C., Meek, C. & Richardson, T. (1999), “Truth Is Among the Best Explanations: Finding Causal Explanations of Conditional Independence and Dependence”, in Computation, Causation, and Discovery, G. Glymour & G. Cooper, eds., MIT Press, Cambridge, 167–209.Google Scholar
  39. Shipley, B. (1997), “Exploratory Path Analysis with Applications in Ecology and Evolution”, American Naturalist 149, 1113–1138.CrossRefGoogle Scholar
  40. Shipley, B. (2000), Cause and Correlation in Biology: A User's Guide to Path Analysis, Structural Equations and Causal Inference, Cambridge University Press, Cambridge.Google Scholar
  41. Silva, R., Scheines, R., Glymour, C. & Spirtes, P. (2003), “Learning Measurement Models for Unobserved Variables”, in Proceedings of the Nineteenth Conference on Uncertainty in Artificial Intelligence, Morgan Kaufmann, San Francisco.Google Scholar
  42. Spirtes, P., Glymour, C. & Scheines, R. (2000), Causation, Prediction, and Search, 2. ed., MIT Press, Cambridge.MATHGoogle Scholar
  43. Spirtes, P., Meek, C. & Richardson, T. (1999), “An Algorithm for Causal Inference in the Presence of Latent Variables and Selection Bias”, in Computation, Causation, and Discovery, G. Glymour & G. Cooper, eds., MIT Press, Cambridge, 211–252.Google Scholar
  44. Spirtes, P., Richardson, T., Meek, C., Scheines, R. & Glymour, C. (1996), “Using D-separation to Calculate Zero Partial Correlations in Linear Models with Correlated Errors”, Technical Report CMU-Phil-72, Canegie Mellon University, Pittsburgh.Google Scholar
  45. Spirtes, P., Richardson, T., Meek, C., Scheines, R. & Glymour, C. (1998), “Using Path Diagrams as a Structural Equation Modeling Tool”, Sociological Methods and Research 27, 182–225.Google Scholar
  46. Stelzl, I. (1986), “Changing a Causal Hypothesis Without Changing the Fit: Some Rules for Generating Equivalent Path Models”, Multivariate Behavioral Research 21, 309–331.CrossRefGoogle Scholar
  47. Verma, T. (1993), “Graphical Aspects of Causal Models”, Technical Report R-191, Computer Science Department, UCLA, Los Angeles.Google Scholar
  48. Verma, T. & Pearl, J. (1990), “Equivalence and Synthesis of Causal Models”, in Proceedings of the Sixth Conference on Uncertainty in Artificial Intelligence, Morgan Kaufmann, San Francisco, 220–227.Google Scholar

Copyright information

© Springer-Verlag 2006

Authors and Affiliations

  • Dirk Temme
    • 1
  1. 1.Institute of MarketingHumboldt-University BerlinBerlin

Personalised recommendations