Advertisement

Optimal Structural Nested Models for Optimal Sequential Decisions

  • James M. Robins
Part of the Lecture Notes in Statistics book series (LNS, volume 179)

Abstract

I describe two new methods for estimating the optimal treatment regime (equivalently, protocol, plan or strategy) from very high dimesional observational and experimental data: (i) g-estimation of an optimal double-regime structural nested mean model (drSNMM) and (ii) g-estimation of a standard single regime SNMM combined with sequential dynamic-programming (DP) regression. These methods are compared to certain regression methods found in the sequential decision and reinforcement learning literatures and to the regret modelling methods of Murphy (2003). I consider both Bayesian and frequentist inference. In particular, I propose a novel “Bayes-frequentist compromise” that combines honest subjective non- or semiparametric Bayesian inference with good frequentist behavior, even in cases where the model is so large and the likelihood function so complex that standard (uncompromised) Bayes procedures have poor frequentist performance.

Keywords

Sequential Randomization Influence Function Optimal Regime Sequential Decision Closed Linear Span 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Bibliography

  1. Baraud, Y. (2002). Confidence balls in Gaussian regression, (to appear).Google Scholar
  2. Bertsekas, D.P. and Tsitsiklis, J.N. (1996). Neuro-dynamic programming. Belmont MA: Athena Scientific.zbMATHGoogle Scholar
  3. Bickel, P.J. and Ritov, Y. (1988). Estimating integrated squared density derivatives: sharp best order of convergence estimates. Sankya Ser. A 50: 381–393.MathSciNetzbMATHGoogle Scholar
  4. Bickel, P.J., Klaassen, C., Ritov, Y., and Wellner, J. (1993). Efficient and adapted estimation for semiparametric models. Johns Hopkins, Baltimore.Google Scholar
  5. Cowell, R.G., Dawid, A.P., Lauritzen, S.L, and Spiegelhalter, D.J. (1999). Probabilistic networks in expert systems, New York: Springer-Verlag.Google Scholar
  6. Donald, S.G. and Newey, W.K. (1994). Series estimation of the semilinear models. Journal of Multivariate Analysis, 5): 30–40.MathSciNetCrossRefGoogle Scholar
  7. Gill, R.D. and Robins, J.M. (2001). Causal inference for complex longitudinal data: the continuous case. Annals of Statistics, 29(6): 1785–1811MathSciNetzbMATHCrossRefGoogle Scholar
  8. Hoffman, M. and Lepski, O. (2002). Random rates and anisotropic regression (with discussion and rejoinder). Annals of Statistics, 30: 325–396.MathSciNetCrossRefGoogle Scholar
  9. Li, KC. (1989). Honest Confidence Regions for Nonparametric Regression. The Annals of Statistics, 17(3):1001–1008.MathSciNetzbMATHCrossRefGoogle Scholar
  10. Laurent, B. (1996). Efficient estimation of integral functionals of a density. Annals of Statistics, 24(2): 659–681.MathSciNetzbMATHCrossRefGoogle Scholar
  11. Laurent, B. and Massart, P. (2000). Adaptive estimation of a quadratic functional by model selection. Annals of Statistics, 28(5): 1302–1338.MathSciNetzbMATHCrossRefGoogle Scholar
  12. Murphy, Susan. (2003). Optimal dynamic treatment regimes. Journal of the Royal Statistical Society B, 65(2):331–355.zbMATHCrossRefGoogle Scholar
  13. Ritov, Y. and Bickel, P. (1990) Achieving information bounds in non-and semi-parametric models. Annals of Statistics, 18: 925–938.MathSciNetzbMATHCrossRefGoogle Scholar
  14. Robins, J.M. (1986). A new approach to causal inference in mortality studies with sustained exposure periods-Application to control of the healthy worker survivor effect. Mathematical Modelling, 7:1393–1512MathSciNetzbMATHCrossRefGoogle Scholar
  15. Robins, J.M. (1994). Correcting for non-compliance in randomized trials using structural nested mean models. Communications in Statistics, 23:2379–2412.MathSciNetzbMATHCrossRefGoogle Scholar
  16. Robins, J.M. (1997). Causal Inference from Complex Longitudinal Data. Latent Variable Modeling and Applications to Causality. Lecture Notes in Statistics (120), M. Berkane, Editor. NY: Springer Verlag, pp. 69–117.CrossRefGoogle Scholar
  17. Robins, J.M. (1998a). Correction for non-compliance in equivalence trials. Statistics in Medicine, 17:269–302.CrossRefGoogle Scholar
  18. Robins, J.M., (1998b) Structural nested failure time models. Survival Analysis, P.K. Anderson and N. Keiding, Section Editors. The Encyclopedia of Biostatistics. P. Armitage and T. Colton, Editors. Chichester, UK: John Wiley & Sons. pp 4372–4389.Google Scholar
  19. Robins, J.M. (1999). Marginal Structural Models versus Structural Nested Models as Tools for Causal Inference. Statistical Models in Epidemiology: The Environment and Clinical Trials. M.E. Halloran and D. Berry, Editors, IMA Volume 116, NY: Springer-Verlag, pp. 95–134.Google Scholar
  20. Robins, J.M. (2000). Robust estimation in sequentially ignorable missing data and causal inference models. Proceedings of the American Statistical Association Section on Bayesian Statistical Science 1999, pp. 6–10.Google Scholar
  21. Robins, J.M., Greenland, S. and Hu F-C. (1999). Rejoinder to Comments on “Estimation of the causal effect of a time-varying exposure on the marginal mean of a repeated binary outcome.” Journal of the American Statistical Association, Applications and Case Studies, 94:708–712.MathSciNetGoogle Scholar
  22. Robins, J.M. and Ritov, Y. (1997). Toward a curse of dimensionality appropriate (CODA) asymptotic theory for semi-parametric models. Statistics in Medicine, 16:285–319.CrossRefGoogle Scholar
  23. Robins J.M. and Rotnitzky A. (2001). Comment on the Bickel and Kwon article, “Inference for semiparametric models: Some questions and an answer” Statistica Sinica, 11(4):920–936. [“On Double Robustness.”]Google Scholar
  24. Robins, J.M. and Rotnitzky, A. (2003). Direct effects structural nested mean models. Annals of Statistics, (under review).Google Scholar
  25. Robins, J.M., Rotnitzky, A. and Scharfstein, D. (1999a). Sensitivity Analysis for Selection Bias and Unmeasured Confounding in Missing Data and Causal Inference Models. In: Statistical Models in Epidemiology: The Environment and Clinical Trials. Halloran, E. and Berry, D., eds. IMA Volume 116, NY: Springer-Verlag, pp. 1–92.CrossRefGoogle Scholar
  26. Robins J.M., Rotnitzky A., van der Laan M. (2000). Comment on “On Profile Likelihood” by Murphy SA and van der Vaart AW. Journal of the American Statistical Association-Theory and Methods, 95(450):431–435.Google Scholar
  27. Robins, J.M., Scheines, R., Spirtes, P., and Wasserman, L.(2003). Uniform consistency in causal inference. Biometrika, 90(3):491–515.MathSciNetCrossRefGoogle Scholar
  28. Robins, J.M. and Wasserman L. (1997). Estimation of Effects of Sequential Treatments by Reparameterizing Directed Acyclic Graphs. Proceedings of the Thirteenth Conference on Uncertainty in Artificial Intelligence, Providence Rhode Island, August 1–3, 1997. Dan Geiger and Prakash Shenoy (Eds.), Morgan Kaufmann, San Francisco, pp. 409–420.Google Scholar
  29. Robins, J.M. and van der Vaart, A.W. (2003). Non parametric confidence sets by cross-validation. (Technical Report).Google Scholar
  30. Robins, J.M. and van der Vaart, A.W. (2004). A unified approach to estimation in non-semiparametric models using higher order influence functions. (Technical Report)Google Scholar
  31. Small, C.G. and McLeish, D. (1994). Hilbert space methods in probability and statistical inference. New York: Wiley.zbMATHCrossRefGoogle Scholar
  32. Sutton, R.S. and Barto, A.G. (1998). Reinforcement learning: An introduction. Cambridge, MA: MIT Press.Google Scholar
  33. van der Laan, M. and Dudoit (2003) Asymptotics of cross-validated risk estimation in model selection and performance assessment, revised for publication in Annals of Statistics.Google Scholar
  34. van der Laan, M.J., Murphy, S., and Robins, J.M. (2003). Marginal structural nested models. (to be submitted).Google Scholar
  35. van der Laan M.J., Robins JM (1998). Locally efficient estimation with current status data and time-dependent covariates. Journal of the American Statistical Association, 93:693–701.MathSciNetzbMATHCrossRefGoogle Scholar
  36. van der Laan, M. and Robins, J.M. (2002). Unified methods for censored longitudinal data and causality. Springer-Verlag.Google Scholar
  37. van der Vaart, A.W. (1991). On differentiable functionals. Annals of Statistics, 19:178–204.MathSciNetzbMATHCrossRefGoogle Scholar
  38. Waterman, R.P. and Lindsay, B.G. (1996). Projected score methods for approximating conditional scores. Biometrika, 83(1): 1–13.MathSciNetzbMATHCrossRefGoogle Scholar
  39. Wegkamp, TM. (2003) Model selection in nonparametric regression. Annals of Statistics, 31(1):252–273.MathSciNetzbMATHCrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2004

Authors and Affiliations

  • James M. Robins
    • 1
  1. 1.Departments of Epidemiology and BiostatisticsHarvard School of Public HealthBostonUSA

Personalised recommendations