The aim of this project is to study and extend a general statistical methodology, called Targeted Empirical Learning, which includes a recently developed Targeted Maximum Likelihood methodology. The fundamental theoretical underpinnings of this new and unified approach to statistical learning have been developed and we propose to expand Targeted Empirical Learning into a practical product that can be applied to pressing scientific questions. Building on long-standing collaborations with leading scientists in the areas of clinical AIDS research, we will use this novel methodology to address research questions concerning HIV. Given observed data consisting of a realization of n independently and identically distributed random variables, Targeted Empirical Learning employs the following elements: i) defining the parameter of interest; 2) modeling the parameter of interest, leaving the nuisance parameters unspecified or only including truly known modeling assumptions; 3) developing targeted robust and highly efficient (maximum likelihood) estimators of the parameter of interest. The methodology relies on unified cross- validation to choose between competitive estimators indexed by, for example, choices of sieves parameterizations, algorithms, and/or dimension reductions (in particular for the nuisance parameters). Importantly, the cross-validation criterion employed evaluates the performance of these candidate estimators with respect to the parameter of interest. Specific applications to be addressed include the following: i) develop models and corresponding targeted empirical learners of optimal individualized treatment rules for treating HIV-infected patients, 2) estimate measures of variable importance/causal effects for mutations in the HIV virus for predicting clinical response to drug combinations; 3) estimate causal effects of adherence profiles on virologic suppression for HIV-infected patients. We will further develop and apply a novel resampling-based multiple testing methodology to properly address our simultaneous testing and estimation of many scientific parameters of interest. ? ? ?

Agency
National Institute of Health (NIH)
Institute
National Institute of Allergy and Infectious Diseases (NIAID)
Type
Research Project (R01)
Project #
5R01AI074345-02
Application #
7447417
Study Section
AIDS Clinical Studies and Epidemiology Study Section (ACE)
Program Officer
Gezmu, Misrak
Project Start
2007-07-01
Project End
2012-06-30
Budget Start
2008-07-01
Budget End
2009-06-30
Support Year
2
Fiscal Year
2008
Total Cost
$458,533
Indirect Cost
Name
University of California Berkeley
Department
Type
Schools of Public Health
DUNS #
124726725
City
Berkeley
State
CA
Country
United States
Zip Code
94704
Zheng, Wenjing; Luo, Zhehui; van der Laan, Mark J (2018) Marginal Structural Models with Counterfactual Effect Modifiers. Int J Biostat 14:
Balzer, Laura B; Zheng, Wenjing; van der Laan, Mark J et al. (2018) A new approach to hierarchical data analysis: Targeted maximum likelihood estimation for the causal effect of a cluster-level exposure. Stat Methods Med Res :962280218774936
Benkeser, David; Ju, Cheng; Lendle, Sam et al. (2018) Online cross-validation-based ensemble learning. Stat Med 37:249-260
Luedtke, Alexander R; van der Laan, Mark J (2018) Parametric-rate inference for one-sided differentiable parameters. J Am Stat Assoc 113:780-788
Koss, Catherine A; Ayieko, James; Mwangwa, Florence et al. (2018) Early Adopters of Human Immunodeficiency Virus Preexposure Prophylaxis in a Population-based Combination Prevention Study in Rural Kenya and Uganda. Clin Infect Dis 67:1853-1860
Zheng, Wenjing; Balzer, Laura; van der Laan, Mark et al. (2018) Constrained binary classification using ensemble learning: an application to cost-efficient targeted PrEP strategies. Stat Med 37:261-279
Chambaz, Antoine; Zheng, Wenjing; van der Laan, Mark J (2017) TARGETED SEQUENTIAL DESIGN FOR TARGETED LEARNING INFERENCE OF THE OPTIMAL TREATMENT RULE AND ITS MEAN REWARD. Ann Stat 45:2537-2564
Sofrygin, Oleg; van der Laan, Mark J (2017) Semi-Parametric Estimation and Inference for the Mean Outcome of the Single Time-Point Intervention in a Causally Connected Population. J Causal Inference 5:
van der Laan, Mark (2017) A Generally Efficient Targeted Minimum Loss Based Estimator based on the Highly Adaptive Lasso. Int J Biostat 13:
Neugebauer, Romain; Schmittdiel, Julie A; Adams, Alyce S et al. (2017) Identification of the joint effect of a dynamic treatment intervention and a stochastic monitoring intervention under the no direct effect assumption. J Causal Inference 5:

Showing the most recent 10 out of 104 publications