Optimal Structural Nested Models for Optimal Sequential Decisions

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.

[1]  O. Lepski,et al.  Random rates in anisotropic regression (with a discussion and a rejoinder by the authors) , 2002 .

[2]  J. Robins.  A new approach to causal inference in mortality studies with a sustained exposure period—application to control of the healthy worker survivor effect , 1986 .

[3]  Christopher G. Small,et al.  Hilbert Space Methods in Probability and Statistical Inference: Small/Hilbert , 1994 .

[4]  P. Bickel,et al.  Achieving Information Bounds in Non and Semiparametric Models , 1990 .

[5]  S. Murphy,et al.  Optimal dynamic treatment regimes , 2003 .

[6]  A. W. van der Vaart,et al.  On Profile Likelihood , 2000 .

[7]  P. Massart,et al.  Adaptive estimation of a quadratic functional by model selection , 2000 .

[8]  James M. Robins,et al.  Causal inference for complex longitudinal data: the continuous case , 2001 .

[9]  Sandrine Dudoit,et al.  Asymptotics of Cross-Validated Risk Estimation in Model Selection and Performance Assessment , 2003 .

[10]  Aad Van Der Vbart,et al.  ON DIFFERENTIABLE FUNCTIONALS , 1988 .

[11]  James M. Robins,et al.  Locally efficient estimation with current status data and time-dependent covariates , 1998 .

[12]  S. Dudoit,et al.  Asymptotics of cross-validated risk estimation in estimator selection and performance assessment , 2005 .

[13]  K. Do,et al.  Efficient and Adaptive Estimation for Semiparametric Models. , 1994 .

[14]  John N. Tsitsiklis,et al.  Neuro-Dynamic Programming , 1996, Encyclopedia of Machine Learning.

[15]  C. Small,et al.  Hilbert Space Methods in Probability and Statistical Inference , 1994 .

[16]  James M. Robins,et al.  Causal Inference from Complex Longitudinal Data , 1997 .

[17]  Peter J. Bickel,et al.  INFERENCE FOR SEMIPARAMETRIC MODELS: SOME QUESTIONS AND AN ANSWER , 2001 .

[18]  Maia Berkane.  Latent Variable Modeling and Applications to Causality , 1997 .

[19]  Yuhong Yang.  MODEL SELECTION FOR NONPARAMETRIC REGRESSION , 1997 .

[20]  J M Robins,et al.  Correction for non-compliance in equivalence trials. , 1998, Statistics in medicine.

[21]  Ronald L. Iman,et al.  Rejoinder to comments , 1980 .

[22]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[23]  J. Robins.  Correcting for non-compliance in randomized trials using structural nested mean models , 1994 .

[24]  Yannick Baraud,et al.  Confidence balls in Gaussian regression , 2004 .

[25]  Rupert G. Miller,et al.  Survival Analysis , 2022, The SAGE Encyclopedia of Research Design.

[26]  James M. Robins,et al.  Estimation of Effects of Sequential Treatments by Reparameterizing Directed Acyclic Graphs , 1997, UAI.

[27]  C. Klaassen,et al.  Discussion to "Inference for semiparametric models: some questions and an answer" by Peter J. Bickel and Jaimyoung Kwon , 2001 .

[28]  P. Bickel.  Efficient and Adaptive Estimation for Semiparametric Models , 1993 .

[29]  J. Robins,et al.  Estimation of the Causal Effect of a Time-Varying Exposure on the Marginal Mean of a Repeated Binary Outcome , 1999 .

[30]  Ker-Chau Li,et al.  Honest Confidence Regions for Nonparametric Regression , 1989 .

[31]  Stephen G. Donald,et al.  Series estimation of semilinear models , 1994 .

[32]  James M. Robins,et al.  Marginal Structural Models versus Structural nested Models as Tools for Causal inference , 2000 .

[33]  D. Berry,et al.  Statistical models in epidemiology, the environment, and clinical trials , 2000 .

[34]  James M. Robins,et al.  On Profile Likelihood: Comment , 2000 .

[35]  J. Robins,et al.  Toward a curse of dimensionality appropriate (CODA) asymptotic theory for semi-parametric models. , 1997, Statistics in medicine.

[36]  J. Robins,et al.  Sensitivity Analysis for Selection bias and unmeasured Confounding in missing Data and Causal inference models , 2000 .

[37]  J. Robins,et al.  Uniform consistency in causal inference , 2003 .

[38]  James M. Robins,et al.  Unified Methods for Censored Longitudinal Data and Causality , 2003 .

[39]  B. Laurent.  Efficient estimation of integral functionals of a density , 1996 .

[40]  Bruce G. Lindsay,et al.  Projected score methods for approximating conditional scores , 1996 .

[41]  David J. Spiegelhalter,et al.  Probabilistic Networks and Expert Systems , 1999, Information Science and Statistics.