Proximal Causal Inference for Complex Longitudinal Studies

• Activity Number: 196 - Biometrics Section Early-Career Paper Award Session
• Type: Topic Contributed
• Date/Time: Monday, August 8, 2022 : 2:00 PM to 3:50 PM
• Sponsor: Biometrics Section
• Author(s): Andrew Ying* and Wang Miao and Xu Shi and Eric J Tchetgen Tchetgen
• Companies: University of Pennsylvania and Peking University and University of Michigan and University of Pennsylvania
• Keywords: Proximal causal inference; Marginal structural mean model; Unmeasured confounding; Semiparametric theory; Double robustness; Longitudinal data

Abstract

A standard assumption for causal inference about the joint effects of time-varying treatment is that one has measured sufficient covariates to ensure that within covariate strata, subjects are exchangeable across observed treatment values, also known as ``sequential randomization assumption (SRA)''. Realistically, measured covariates can rarely capture all confounders with certainty, thus invalidating inferences under SRA. We extend the proximal causal inference (PCI) framework of Miao et al. (2018) to the longitudinal setting under a semiparametric marginal structural mean model (MSMM). PCI offers an opportunity to learn about joint causal effects in settings where SRA based on measured time-varying covariates fails, by formally accounting for the covariate measurements as imperfect proxies of underlying confounding mechanisms. We establish nonparametric identification with a pair of time-varying proxies and provide a corresponding characterization of regular and asymptotically linear estimators of the parameter indexing the MSMM. Extensive simulation studies and a data application illustrate the finite sample behavior of proposed methods.