The principal aim of this proposal is to further development of new methods for analyzing observational data bases and randomized trials of HIV-infected persons and the application of these methods to data obtained in randomized and observational studies in an attempt to help answer important open substantive questions concerning the treatment and course of HlV-related disease. The proposed approaches are based either on (i) the estimation of new classes of causal models which include structural nested models, marginal structural models (MSMs), direct effect structural nested models, continuous time structural nested models, and optimail regime structural models (SNMs). Many of the new methods are fundamentally """"""""epidemiologic"""""""" in that they require data on time-dependent confounding factors, that is, risk factors for outcomes that also predict subsequent treatment with the drug or cofactor under study. In particular, we plan to further develop optimal regime SNMs and dynamic MSMs to help detemnine the optimal times to start HAART therapy and to change HAART regimens as a function of a subject's CD4 count, HIV RNA, clinical history, and, where available, results of genot^lc or phenotypic resistance testing. Our methods will be developed with the goal of directing analyzes and reanalyzes, with collaborators, of data from the HIV Causal Colioboration at HSPH . the Multicenler AIDS Cohort Study, The Women's Interagency HIV Study, The Swiss HIV Cohort Study, The Study of The Consequences of Protease Inhibitor Era (SCOPE), Pediatric Late Outcomes Protocol (PACTG 219) and the ALLRT study.
Observational methods are used to answer pressing causal questions that cannot be or have not yet been studied in randomized trials. In particular we are developing methods that are the best available to determine the optimal CD4 and HIV RNA levels at which to initiate HAAART therapy in HIV infected subjects and the optimal time to change therapy once resistance to a initial HAART regime has developed.
|Ford, Deborah; Robins, James M; Petersen, Maya L et al. (2015) The Impact of Different CD4 Cell-Count Monitoring and Switching Strategies on Mortality in HIV-Infected African Adults on Antiretroviral Therapy: An Application of Dynamic Marginal Structural Models. Am J Epidemiol 182:633-43|
|Robins, James M; VanderWeele, Tyler J; Gill, Richard D (2015) A proof of Bell's inequality in quantum mechanics using causal interactions. Scand Stat Theory Appl 42:329-335|
|Swanson, Sonja A; Robins, James M; Miller, Matthew et al. (2015) Selecting on treatment: a pervasive form of bias in instrumental variable analyses. Am J Epidemiol 181:191-7|
|Vanderweele, Tyler J; Vansteelandt, Stijn; Robins, James M (2014) Effect decomposition in the presence of an exposure-induced mediator-outcome confounder. Epidemiology 25:300-6|
|Gilbert, Peter B; Yu, Xuesong; Rotnitzky, Andrea (2014) Optimal auxiliary-covariate-based two-phase sampling design for semiparametric efficient estimation of a mean or mean difference, with application to clinical trials. Stat Med 33:901-17|
|Lei, Jing; Robins, James; Wasserman, Larry (2013) Distribution Free Prediction Sets. J Am Stat Assoc 108:278-287|
|Lajous, Martin; Willett, Walter C; Robins, James et al. (2013) Changes in fish consumption in midlife and the risk of coronary heart disease in men and women. Am J Epidemiol 178:382-91|
|Haneuse, S; Rotnitzky, A (2013) Estimation of the effect of interventions that modify the received treatment. Stat Med 32:5260-77|
|Li, Lingling; Shen, Changyu; Li, Xiaochun et al. (2013) On weighting approaches for missing data. Stat Methods Med Res 22:14-30|
|HernÃ¡n, Miguel A; HernÃ¡ndez-DÃaz, Sonia; Robins, James M (2013) Randomized trials analyzed as observational studies. Ann Intern Med 159:560-2|
Showing the most recent 10 out of 15 publications