Efficient Estimation of Optimal Regimes Under a No Direct Effect Assumption. Issue 533 (2nd January 2021)

• Record Type: Journal Article
• Authors: Liu, Lin; Shahn, Zach; Robins, James M.; Rotnitzky, Andrea
• Is Part Of: Journal of the American Statistical Association. Volume 116:Issue 533(2021)
• Page Start: 224
• Page End: 239
• Publication Date: 2021-01-02
• Subjects: Direct effects -- Nuisance tangent space -- Optimal dynamic regimes -- Optimal regime structural nested mean models -- Screening; Statistics -- Periodicals; Statistics -- Periodicals; Statistiques -- Périodiques; États-Unis -- Statistiques -- Périodiques; 519.5
• DOI: 10.1080/01621459.2020.1856117
• Languages: English
• ISSNs: 0162-1459

Abstract

Abstract: We derive new estimators of an optimal joint testing and treatment regime under the no direct effect (NDE) assumption that a given laboratory, diagnostic, or screening test has no effect on a patient's clinical outcomes except through the effect of the test results on the choice of treatment. We model the optimal joint strategy with an optimal structural nested mean model (opt-SNMM). The proposed estimators are more efficient than previous estimators of the parameters of an opt-SNMM because they efficiently leverage the "NDE of testing" assumption. Our methods will be of importance to decision scientists who either perform cost-benefit analyses or are tasked with the estimation of the "value of information" supplied by an expensive diagnostic test (such as an MRI to screen for lung cancer). Supplementary materials for this article are available online.