Biometrika Advance Access originally published online on October 1, 2009
Biometrika 2009 96(4):998-1004; doi:10.1093/biomet/asp043
Miscellanea |
A note on the variance of doubly-robust G-estimators
Department of Epidemiology, Biostatistics, & Occupational Health, McGill University, 1020 Pine Ave W., Montreal, Quebec, Canada H3A 1A2 erica.moodie{at}mcgill.ca
Received for publication 1 April 2008. Revision received 1 January 2009.
A recursive variance calculation is derived for doubly-robust G-estimators for dynamic treatment regimes in a multi-interval setting. Treatment decision parameters are not assumed to be shared across treatment intervals; this independence of parameters permits sequential estimation of the G-estimators variance when G-estimation is performed in a sequential fashion. The recursive variance calculation is both natural and computationally feasible. This development can easily be adapted to other complex estimating procedures that require nuisance parameter estimation.
Key Words: Dynamic treatment regime G-estimation Sequential estimation Structural nested mean model
References
-
Bellman R. Dynamic Programming (1957) Princeton, NJ: Princeton University Press.
Hernán M. A., Brumback B., Robins J. M. Marginal structural models to estimate the causal effect of zidovudine on the survival of HIV-positive men. Epidemiol. (2000) 11:561–70.[CrossRef][Web of Science][Medline]
Hernán M. A., Lanoy E., Costagliola D., Robins J. M. Comparison of dynamic treatment regimes via inverse probability weighting. Basic Clin. Pharmacol. Toxicol. (2006) 98:237–42.[CrossRef][Web of Science][Medline]
Moodie E. E. M., Richardson T. S., Stephens D. A. Demystifying optimal dynamic treatment regimes. Biometrics (2007) 63:447–55.[CrossRef][Web of Science][Medline]
Murphy S. A. Optimal dynamic treatment regimes (with discussion). J. R. Statist. Soc. B (2003) 65:331–66.[CrossRef]
Murphy S. A., van der Laan M. J., Robins J. M. Marginal mean models for dynamic treatment regimens. J. Am. Statist. Assoc. (2001) 96:1410–24.[CrossRef][Web of Science]
Nemhauser G. Introduction to Dynamic Programming (1966) New York: Wiley.
Robins J. M. A new approach to causal inference in mortality studies with sustained exposure periods: application to control of the healthy worker survivor effect. Math. Mod. (1986) 7:1393–1512.[CrossRef]
Robins J. M. Causal inference from complex longitudinal data. In: Latent Variable Modeling and Applications to Causality (1997) New York: Springer. 69–117.
Robins J. M. Association, causation, and marginal structural models. Synthese (1999) 121:151–79.[CrossRef][Web of Science]
Robins J. M. Optimal structural nested models for optimal sequential decisions. In: Proceedings of the Second Seattle Symposium on Biostatistics—Lin D. Y., Heagerty P. J., eds. (2004) New York: Springer. 189–326.
Robins J. M., Hernán M. A., Brumback B. Marginal structural models and causal inference in epidemiology. Epidemiol. (2000) 11:550–60.[CrossRef][Web of Science][Medline]
Robins J. M., Orellana L., Rotnitzky A. Estimation and extrapolation of optimal treatment and testing strategies. Statist. Med. (2008) 27:4678–4721.[CrossRef]
Thall P. F., Millikan R. E., Sung H.-G. Evaluating multiple treatment courses in clinical trials. Statist. Med. (2000) 19:1011–28.[CrossRef]
| ||||||||||||||||||||||||||||||||||||||||||||||